{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T22:46:20Z","timestamp":1776120380097,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":40,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,26]]},"DOI":"10.1145\/3706599.3719790","type":"proceedings-article","created":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T20:40:13Z","timestamp":1745440813000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Interactive Sketchpad: A Multimodal Tutoring System for Collaborative, Visual Problem-Solving"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7957-8102","authenticated-orcid":false,"given":"Jimin","family":"Lee","sequence":"first","affiliation":[{"name":"Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA and Multisensory Intelligence, MIT Media Lab, Cambridge, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7560-4146","authenticated-orcid":false,"given":"Steven-Shine","family":"Chen","sequence":"additional","affiliation":[{"name":"Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA and Multisensory Intelligence, MIT Media Lab, Cambridge, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7768-3610","authenticated-orcid":false,"given":"Paul Pu","family":"Liang","sequence":"additional","affiliation":[{"name":"Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA and Multisensory Intelligence, MIT Media Lab, Cambridge, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,4,25]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Abraham Arcavi. 2003. The role of visual representations in the learning of mathematics. Educational studies in mathematics 52 3 (2003) 215\u2013241.","DOI":"10.1023\/A:1024312321077"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627217.3627233"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Hamsa Bastani Osbert Bastani Alp Sungu Haosen Ge Ozge Kabakc\u0131 and Rei Mariman. 2024. Generative ai can harm learning. Available at SSRN 4895486 (2024).","DOI":"10.2139\/ssrn.4895486"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Eliza Bobek and Barbara Tversky. 2016. Creating visual explanations improves learning. Cognitive research: principles and implications 1 (2016) 1\u201314.","DOI":"10.1186\/s41235-016-0031-6"},{"key":"e_1_3_3_1_6_2","unstructured":"Wenhu Chen Xueguang Ma Xinyi Wang and William\u00a0W. Cohen. 2023. Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks. Transactions on Machine Learning Research (2023). https:\/\/openreview.net\/forum?id=YfZ4ZPt8zd"},{"key":"e_1_3_3_1_7_2","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano et\u00a0al. 2021. Training verifiers to solve math word problems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2110.14168 (2021)."},{"key":"e_1_3_3_1_8_2","volume-title":"First Conference on Language Modeling","author":"Fu Deqing","year":"2024","unstructured":"Deqing Fu, Ruohao Guo, Ghazal Khalighinejad, Ollie Liu, Bhuwan Dhingra, Dani Yogatama, Robin Jia, and Willie Neiswanger. 2024. IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations. In First Conference on Language Modeling. https:\/\/openreview.net\/forum?id=KZd1EErRJ1"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Arthur\u00a0C Graesser Shulan Lu George\u00a0Tanner Jackson Heather\u00a0Hite Mitchell Mathew Ventura Andrew Olney and Max\u00a0M Louwerse. 2004. AutoTutor: A tutor with dialogue in natural language. Behavior Research Methods Instruments & Computers 36 (2004) 180\u2013192.","DOI":"10.3758\/BF03195563"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"e_1_3_3_1_11_2","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Hu Yushi","year":"2024","unstructured":"Yushi Hu, Weijia Shi, Xingyu Fu, Dan Roth, Mari Ostendorf, Luke Zettlemoyer, Noah\u00a0A. Smith, and Ranjay Krishna. 2024. Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=GNSMl1P5VR"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3631802.3631806"},{"key":"e_1_3_3_1_13_2","unstructured":"Sal Khan. 2023. Harnessing GPT-4 so that all students benefit. A nonprofit approach for equal access. Khan Academy Blog (2023)."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3701571.3701590"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3636555.3636860"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Paul\u00a0Pu Liang Amir Zadeh and Louis-Philippe Morency. 2024. Foundations & trends in multimodal machine learning: Principles challenges and open questions. Comput. Surveys 56 10 (2024) 1\u201342.","DOI":"10.1145\/3656580"},{"key":"e_1_3_3_1_17_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Lightman Hunter","year":"2024","unstructured":"Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2024. Let\u2019s Verify Step by Step. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=v8L0pN6EOi"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.528"},{"key":"e_1_3_3_1_19_2","unstructured":"Liliana Mata Gabriel Lazar and Iuliana Lazar. 2016. Interactive Whiteboards for Teaching and Learning Science: Ascertaining Research. Online Submission 20 2 (2016) 135\u2013148."},{"key":"e_1_3_3_1_20_2","volume-title":"The GPT Surprise: Offering Large Language Model Chat in a Massive Coding Class Reduced Engagement but Increased Adopters\u2019 Exam Performances","author":"Nie Allen","year":"2024","unstructured":"Allen Nie, Yash Chandak, Miroslav Suzara, Ali Malik, Juliette Woodrow, Matt Peng, Mehran Sahami, Emma Brunskill, and Chris Piech. 2024. The GPT Surprise: Offering Large Language Model Chat in a Massive Coding Class Reduced Engagement but Increased Adopters\u2019 Exam Performances. Technical Report. Center for Open Science."},{"key":"e_1_3_3_1_21_2","unstructured":"OpenAI. 2024. GPT-4o System Card. ArXiv abs\/2410.21276 (2024). https:\/\/api.semanticscholar.org\/CorpusID:273662196"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-36336-8_45"},{"key":"e_1_3_3_1_23_2","unstructured":"Jamal Raiyn. 2016. The Role of Visual Learning in Improving Students\u2019 High-Order Thinking Skills. Journal of Education and Practice 7 24 (2016) 115\u2013121."},{"key":"e_1_3_3_1_24_2","unstructured":"Daniel\u00a0Philip Rose Vaishnavi Himakunthala Andy Ouyang Ryan He Alex Mei Yujie Lu Michael Saxon Chinmay Sonar Diba Mirza and William\u00a0Yang Wang. 2024. Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings. https:\/\/openreview.net\/forum?id=01Yi8rzoNs"},{"key":"e_1_3_3_1_25_2","first-page":"457","volume-title":"Proceedings 30th conference of the International Group for the Psychology of mathematics education","volume":"4","author":"R\u00f6sken Bettina","year":"2006","unstructured":"Bettina R\u00f6sken and Katrin Rolka. 2006. A picture is worth a 1000 words\u2013the role of visualization in mathematics learning. In Proceedings 30th conference of the International Group for the Psychology of mathematics education , Vol.\u00a04. Charles University Prague, 457\u2013464."},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Johanna Schoenherr and Stanislaw Schukajlow. 2024. Characterizing external visualization in mathematics education research: a scoping review. ZDM\u2013Mathematics Education 56 1 (2024) 73\u201385.","DOI":"10.1007\/s11858-023-01494-3"},{"key":"e_1_3_3_1_27_2","unstructured":"Ghulam Shabiralyani Khuram\u00a0Shahzad Hasan Naqvi Hamad and Nadeem Iqbal. 2015. Impact of visual aids in enhancing the learning process case research: District Dera Ghazi Khan. Journal of education and practice 6 19 (2015) 226\u2013233."},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","unstructured":"Hao Shao Shengju Qian Han Xiao Guanglu Song Zhuofan Zong Letian Wang Yu Liu and Hongsheng Li. 2024. Visual CoT: Unleashing Chain-of-Thought Reasoning in Multi-Modal Language Models. CoRR abs\/2403.16999 (2024). 10.48550\/arXiv.2403.16999","DOI":"10.48550\/arXiv.2403.16999"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","unstructured":"Kyvete Shatri and Kastriot Buza. 2017. The Use of Visualization in Teaching and Learning Process for Developing Critical Thinking of Students. European Journal of Social Sciences Education and Research 9 (01 2017) 71. 10.26417\/ejser.v9i1.p71-74","DOI":"10.26417\/ejser.v9i1.p71-74"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.277"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"John Sweller. 1994. Cognitive load theory learning difficulty and instructional design. Learning and instruction 4 4 (1994) 295\u2013312.","DOI":"10.1016\/0959-4752(94)90003-5"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Kurt VanLehn. 2011. The relative effectiveness of human tutoring intelligent tutoring systems and other tutoring systems. Educational psychologist 46 4 (2011) 197\u2013221.","DOI":"10.1080\/00461520.2011.611369"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Huanhuan Wang Ahmed Tlili Ronghuai Huang Zhenyu Cai Min Li Zui Cheng Dong Yang Mengti Li Xixian Zhu and Cheng Fei. 2023. Examining the applications of intelligent tutoring systems in real educational contexts: A systematic literature review from the social experiment perspective. Education and information technologies 28 7 (2023) 9113\u20139148.","DOI":"10.1007\/s10639-022-11555-x"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"crossref","unstructured":"Rose\u00a0E Wang Ana\u00a0T Ribeiro Carly\u00a0D Robinson Susanna Loeb and Dora Demszky. 2024. Tutor CoPilot: A human-AI approach for scaling real-time expertise. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.03017 (2024).","DOI":"10.21203\/rs.3.rs-5363154\/v1"},{"key":"e_1_3_3_1_36_2","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Fei Xia Ed Chi Quoc\u00a0V Le Denny Zhou et\u00a0al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems 35 (2022) 24824\u201324837."},{"key":"e_1_3_3_1_37_2","unstructured":"Changrong Xiao Wenxing Ma Sean\u00a0Xin Xu Kunpeng Zhang Yufang Wang and Qi Fu. 2024. From Automation to Augmentation: Large Language Models Elevating Essay Scoring Landscape. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.06431 (2024)."},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.bea-1.49"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Jialu Zhang Jos\u00e9\u00a0Pablo Cambronero Sumit Gulwani Vu Le Ruzica Piskac Gustavo Soares and Gust Verbruggen. 2024. Pydex: Repairing bugs in introductory python assignments using llms. Proceedings of the ACM on Programming Languages 8 OOPSLA1 (2024) 1100\u20131124.","DOI":"10.1145\/3649850"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Ying Zhang Pengjin Wang Wei Jia Aijun Zhang and Gaowei Chen. 2023. Dynamic visualization by GeoGebra for mathematics learning: a meta-analysis of 20 years of research. Journal of Research on Technology in Education (2023) 1\u201322.","DOI":"10.1080\/15391523.2023.2250886"},{"key":"e_1_3_3_1_41_2","unstructured":"Chunting Zhou Lili Yu Arun Babu Kushal Tirumala Michihiro Yasunaga Leonid Shamis Jacob Kahn Xuezhe Ma Luke Zettlemoyer and Omer Levy. 2024. Transfusion: Predict the next token and diffuse images with one multi-modal model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.11039 (2024)."}],"event":{"name":"CHI EA '25: Extended Abstracts of the CHI Conference on Human Factors in Computing Systems","location":"Yokohama Japan","acronym":"CHI EA '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706599.3719790","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3706599.3719790","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:34Z","timestamp":1750295914000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706599.3719790"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,25]]},"references-count":40,"alternative-id":["10.1145\/3706599.3719790","10.1145\/3706599"],"URL":"https:\/\/doi.org\/10.1145\/3706599.3719790","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"}}]}}