{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T06:47:04Z","timestamp":1782370024177,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":97,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3772318.3790418","type":"proceedings-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T04:12:21Z","timestamp":1776053541000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Codesigning Ripplet: an LLM-Assisted Assessment Authoring System Grounded in a Conceptual Model of Teachers\u2019 Workflows"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2681-6441","authenticated-orcid":false,"given":"Yuan","family":"Cui","sequence":"first","affiliation":[{"name":"Computer Science, Northwestern University, Evanston, Illinois, USA and Computer Science, University of Maryland, College Park, Maryland, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5600-725X","authenticated-orcid":false,"given":"Annabel Marie","family":"Goldman","sequence":"additional","affiliation":[{"name":"Computer Science, Northwestern University, Evanston, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1040-3973","authenticated-orcid":false,"given":"Jovy","family":"Zhou","sequence":"additional","affiliation":[{"name":"Computer Science, Northwestern University, Evanston, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5462-1711","authenticated-orcid":false,"given":"Xiaolin","family":"Liu","sequence":"additional","affiliation":[{"name":"Computer Science, Northwestern University, Evanston, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5657-5872","authenticated-orcid":false,"given":"Clarissa M","family":"Shieh","sequence":"additional","affiliation":[{"name":"Computer Science, Northwestern University, Evanston, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3426-4975","authenticated-orcid":false,"given":"Joshua","family":"Yao","sequence":"additional","affiliation":[{"name":"Computer Science, Northwestern University, Evanston, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2480-3330","authenticated-orcid":false,"given":"Mia Lillian","family":"Cheng","sequence":"additional","affiliation":[{"name":"Computer Science, Northwestern University, Evanston, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9446-0419","authenticated-orcid":false,"given":"Matthew","family":"Kay","sequence":"additional","affiliation":[{"name":"Computer Science and Communication Studies, Northwestern University, Evanston, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8401-2580","authenticated-orcid":false,"given":"Fumeng","family":"Yang","sequence":"additional","affiliation":[{"name":"Computer Science, University of Maryland, College Park, Maryland, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"publisher","unstructured":"2020. Capturing Greater Context for Question Generation. Proceedings of the AAAI Conference on Artificial Intelligence 34 05 (Apr 2020) 9065\u20139072. 10.1609\/aaai.v34i05.6440","DOI":"10.1609\/aaai.v34i05.6440"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","unstructured":"Lenore Adie. 2013. The Development of Teacher Assessment Identity through Participation in Online Moderation. Assessment in Education: Principles Policy & Practice 20 1 (2013) 91\u2013106. 10.1080\/0969594X.2011.650150","DOI":"10.1080\/0969594X.2011.650150"},{"key":"e_1_3_3_3_4_2","volume-title":"Standards for Educational and Psychological Testing","author":"Association American Educational\u00a0Research","year":"2014","unstructured":"American Educational\u00a0Research Association, American\u00a0Psychological Association, and National\u00a0Council on\u00a0Measurement\u00a0in Education. 2014. Standards for Educational and Psychological Testing. American Educational Research Association."},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","unstructured":"Nicole Barnes Helenrose Fives and Charity\u00a0M. Dacey. 2017. U.S. teachers\u2019 conceptions of the purposes of assessment. Teaching and Teacher Education 65 (2017) 107\u2013116. 10.1016\/j.tate.2017.02.017","DOI":"10.1016\/j.tate.2017.02.017"},{"key":"e_1_3_3_3_6_2","volume-title":"Inside the black box: Raising standards through classroom assessment","author":"Black Paul","year":"1998","unstructured":"Paul Black and Dylan Wiliam. 1998. Inside the black box: Raising standards through classroom assessment. Granada Learning."},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"crossref","unstructured":"Paul Black and Dylan Wiliam. 2009. Developing the theory of formative assessment. Educational Assessment Evaluation and Accountability (formerly: Journal of Personnel Evaluation in Education) 21 1 (2009) 5\u201331. 10.1007\/s11092-008-9068-5.","DOI":"10.1007\/s11092-008-9068-5"},{"key":"e_1_3_3_3_8_2","unstructured":"College Board. 2025. Advance Placement (AP) Program. https:\/\/ap.collegeboard.org\/."},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","unstructured":"Virginia Braun and Victoria Clarke. 2006. Using thematic analysis in psychology. Qualitative Research in Psychology 3 2 (2006) 77\u2013101. 10.1191\/1478088706qp063oa","DOI":"10.1191\/1478088706qp063oa"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"crossref","unstructured":"Gavin T.\u00a0L. Brown. 2004. Teachers\u2019 conceptions of assessment: implications for policy and professional development. Assessment in Education: Principles Policy & Practice 11 3 (2004) 301\u2013318.","DOI":"10.1080\/0969594042000304609"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","unstructured":"Gavin T.\u00a0L. Brown. 2006. Teachers\u2019 Conceptions of Assessment: Validation of an Abridged Version. Psychological Reports 99 1 (2006) 166\u2013170. 10.2466\/pr0.99.1.166-170","DOI":"10.2466\/pr0.99.1.166-170"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"crossref","unstructured":"Sally Brown. 2005. Assessment for learning. Learning and teaching in higher education1 (2005) 81\u201389.","DOI":"10.1002\/tl.190"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-36272-9_27"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706599.3719852"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","unstructured":"James Carifio and Rocco Perla. 2008. Resolving the 50-year debate around using and misusing Likert scales. Med Educ 42 12 (Dec 2008) 1150\u20131152. 10.1111\/j.1365-2923.2008.03172.x","DOI":"10.1111\/j.1365-2923.2008.03172.x"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","unstructured":"Guanliang Chen Jie Yang Claudia Hauff and Geert-Jan Houben. 2018. LearningQ: A Large-Scale Dataset for Educational Question Generation. Proceedings of the International AAAI Conference on Web and Social Media 12 1 (2018). 10.1609\/icwsm.v12i1.14987","DOI":"10.1609\/icwsm.v12i1.14987"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.465"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","unstructured":"Zirui Cheng Jingfei Xu and Haojian Jin. 2024. TreeQuestion: Assessing Conceptual Learning Outcomes with LLM-Generated Multiple-Choice Questions. Proceedings of the ACM on Human-Computer Interaction 8 Article 431 (Nov. 2024) 29\u00a0pages. 10.1145\/3686970","DOI":"10.1145\/3686970"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","unstructured":"Erin Cherry and Celine Latulipe. 2014. Quantifying the Creativity Support of Digital Tools through the Creativity Support Index. ACM Trans. Comput.-Hum. Interact. 21 4 Article 21 (June 2014) 25\u00a0pages. 10.1145\/2617588","DOI":"10.1145\/2617588"},{"key":"e_1_3_3_3_20_2","volume-title":"Psychological Testing and Assessment (10th ed.)","author":"Cohen Ronald\u00a0Jay","year":"2022","unstructured":"Ronald\u00a0Jay Cohen, W.\u00a0Joel Schneider, and Ren\u00e9e Tobin. 2022. Psychological Testing and Assessment (10th ed.). McGraw Hill LLC, New York, NY."},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","unstructured":"Andrew Coombs Christopher DeLuca Danielle LaPointe-McEwan and Agnieszka Chalas. 2018. Changing approaches to classroom assessment: An empirical study across teacher career stages. Teaching and Teacher Education 71 (2018) 134\u2013144. 10.1016\/j.tate.2017.12.010","DOI":"10.1016\/j.tate.2017.12.010"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","unstructured":"Yuan Cui Lily\u00a0W. Ge Yiren Ding Lane Harrison Fumeng Yang and Matthew Kay. 2025. Promises and Pitfalls: Using Large Language Models to Generate Visualization Items. IEEE Transactions on Visualization and Computer Graphics 31 1 (2025) 1094\u20131104. 10.1109\/TVCG.2024.3456309","DOI":"10.1109\/TVCG.2024.3456309"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","unstructured":"Christopher DeLuca and Don\u00a0A. Klinger. 2010. Assessment literacy development: identifying gaps in teacher candidates\u2019 learning. Assessment in Education: Principles Policy & Practice 17 4 (2010) 419\u2013438. 10.1080\/0969594x.2010.516643","DOI":"10.1080\/0969594x.2010.516643"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","unstructured":"Christopher DeLuca Danielle LaPointe-McEwan and Ulemu Luhanga. 2016. Teacher assessment literacy: A review of international standards and measures. Educational Assessment Evaluation and Accountability 28 3 (2016) 251\u2013272. 10.1007\/s11092-015-9233-6","DOI":"10.1007\/s11092-015-9233-6"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","unstructured":"Steven\u00a0M. Downing. 2005. The Effects of Violating Standard Item Writing Principles on Tests and Students: The Consequences of Using Flawed Test Items on Achievement Examinations in Medical Education. Advances in Health Sciences Education 10 2 (2005) 133\u2013143. 10.1007\/s10459-004-4019-5","DOI":"10.1007\/s10459-004-4019-5"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","unstructured":"Sabina Elkins Ekaterina Kochmar Iulian Serban and Jackie C.\u00a0K. Cheung. 2023. How Useful Are Educational Questions Generated by Large Language Models? Communications in Computer and Information Science (2023) 536\u2013542. 10.1007\/978-3-031-36336-8_83","DOI":"10.1007\/978-3-031-36336-8_83"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","unstructured":"Haoxiang Fan Guanzheng Chen Xingbo Wang and Zhenhui Peng. 2024. LessonPlanner: Assisting Novice Teachers to Prepare Pedagogy-Driven Lesson Plans with Large Language Models. Article 146 20\u00a0pages. 10.1145\/3654777.3676390","DOI":"10.1145\/3654777.3676390"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713139"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"crossref","unstructured":"Suzanne Fergus Michelle Botha and Mehrnoosh Ostovar. 2023. Evaluating Academic Answers Generated Using ChatGPT. Journal of Chemical Education 100 4 (04 2023) 1672\u20131675.","DOI":"10.1021\/acs.jchemed.3c00087"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","unstructured":"Sandra Ferketich. 1991. Focus on psychometrics. Aspects of item analysis. Research in Nursing & Health 14 2 (1991) 165\u2013168. 10.1002\/nur.4770140211","DOI":"10.1002\/nur.4770140211"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","unstructured":"Yifan Gao Lidong Bing Wang Chen Michael\u00a0R Lyu and Irwin King. 2018. Difficulty Controllable Generation of Reading Comprehension Questions. Proceedings of the International Joint Conference on Artificial Intelligence (2018). 10.48550\/arxiv.1807.03586","DOI":"10.48550\/arxiv.1807.03586"},{"key":"e_1_3_3_3_32_2","unstructured":"John Gardner. 2006. Assessment for learning: A compelling conceptualization. Assessment and learning (2006) 197\u2013204."},{"key":"e_1_3_3_3_33_2","unstructured":"Abdallah Ghaicha. 2016. Theoretical Framework for Educational Assessment: A Synoptic Review. Journal of Education and Practice 7 24 (2016) 212\u2013231."},{"key":"e_1_3_3_3_34_2","first-page":"5925","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"Gong Huanli","year":"2022","unstructured":"Huanli Gong, Liangming Pan, and Hengchang Hu. 2022. KHANQ: A Dataset for Generating Deep Questions in Education. In Proceedings of the 29th International Conference on Computational Linguistics, Nicoletta Calzolari, Chu-Ren Huang, Hansaem Kim, James Pustejovsky, Leo Wanner, Key-Sun Choi, Pum-Mo Ryu, Hsin-Hsi Chen, Lucia Donatelli, Heng Ji, Sadao Kurohashi, Patrizia Paggio, Nianwen Xue, Seokhwan Kim, Younggyun Hahm, Zhong He, Tony\u00a0Kyungil Lee, Enrico Santus, Francis Bond, and Seung-Hoon Na (Eds.). International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 5925\u20135938. https:\/\/aclanthology.org\/2022.coling-1.518\/"},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.4324\/9780203850381"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","unstructured":"Ching\u00a0Nam Hang Chee Wei\u00a0Tan and Pei-Duo Yu. 2024. MCQGen: A Large Language Model-Driven MCQ Generator for Personalized Learning. IEEE Access 12 (2024) 102261\u2013102273. 10.1109\/ACCESS.2024.3420709","DOI":"10.1109\/ACCESS.2024.3420709"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642074"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713731"},{"key":"e_1_3_3_3_39_2","unstructured":"KaTeX Contributors. 2013. KaTeX. https:\/\/katex.org\/."},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376219"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025883"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","unstructured":"Stefan K\u00fcchemann Steffen Steinert Natalia Revenga Matthias Schweinberger Yavuz Dinc Karina\u00a0E. Avila and Jochen Kuhn. 2023. Can ChatGPT support prospective teachers in physics task development? Physical Review Physics Education Research 19 (2023) 020128. Issue 2. 10.1103\/PhysRevPhysEducRes.19.020128","DOI":"10.1103\/PhysRevPhysEducRes.19.020128"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","unstructured":"Ghader Kurdi Jared Leo Bijan Parsia Uli Sattler and Salam Al-Emari. 2020. A Systematic Review of Automatic Question Generation for Educational Purposes. International Journal of Artificial Intelligence in Education 30 1 (2020) 121\u2013204. 10.1007\/s40593-019-00186-y","DOI":"10.1007\/s40593-019-00186-y"},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706599.3719749"},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/1518701.1519023"},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","unstructured":"Jintao Ling and Muhammad Afzaal. 2024. Automatic question-answer pairs generation using pre-trained large language models in higher education. Computers and Education: Artificial Intelligence 6 (2024) 100252. 10.1016\/j.caeai.2024.100252","DOI":"10.1016\/j.caeai.2024.100252"},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"publisher","unstructured":"Anne Looney Joy Cumming Fabienne van Der\u00a0Kleij and Karen\u00a0Harris and. 2018. Reconceptualising the role of teachers as assessors: teacher assessment identity. Assessment in Education: Principles Policy & Practice 25 5 (2018) 442\u2013467. 10.1080\/0969594X.2016.1268090","DOI":"10.1080\/0969594X.2016.1268090"},{"key":"e_1_3_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580957"},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22668-2_19"},{"key":"e_1_3_3_3_50_2","unstructured":"Harsh Maheshwari Srikanth Tenneti and Alwarappan Nakkiran. 2025. CiteFix: Enhancing RAG Accuracy Through Post-Processing Citation Correction. arxiv:https:\/\/arXiv.org\/abs\/2504.15629\u00a0[cs.IR] https:\/\/arxiv.org\/abs\/2504.15629"},{"key":"e_1_3_3_3_51_2","unstructured":"Subhankar Maity Aniket Deroy and Sudeshna Sarkar. 2024. Exploring the capabilities of prompted large language models in educational and assessment applications. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.11579 (2024)."},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3632754.3632755"},{"key":"e_1_3_3_3_53_2","doi-asserted-by":"publisher","unstructured":"Subhankar Maity Aniket Deroy and Sudeshna Sarkar. 2024. How Effective is GPT-4 Turbo in Generating School-Level Questions from Textbooks Based on Bloom\u2019s Revised Taxonomy? arXiv (2024). 10.48550\/arxiv.2406.15211","DOI":"10.48550\/arxiv.2406.15211"},{"key":"e_1_3_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56063-7_18"},{"key":"e_1_3_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642462"},{"key":"e_1_3_3_3_56_2","doi-asserted-by":"publisher","unstructured":"Nora McDonald Sarita Schoenebeck and Andrea Forte. 2019. Reliability and Inter-rater Reliability in Qualitative Research: Norms and Guidelines for CSCW and HCI Practice. Proc. ACM Hum.-Comput. Interact. 3 CSCW Article 72 (Nov. 2019) 23\u00a0pages. 10.1145\/3359174","DOI":"10.1145\/3359174"},{"key":"e_1_3_3_3_57_2","unstructured":"James\u00a0H McMillan. 1999. Establishing High Quality Classroom Assessments. (1999)."},{"key":"e_1_3_3_3_58_2","doi-asserted-by":"crossref","unstructured":"James\u00a0H. McMillan. 2003. Understanding and Improving Teachers\u2019 Classroom Assessment Decision Making: Implications for Theory and Practice. Educational Measurement: Issues and Practice 22 4 (2003) 34\u201343. 10.1111\/j.1745-3992.2003.tb00142.x.","DOI":"10.1111\/j.1745-3992.2003.tb00142.x"},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"crossref","unstructured":"Craig\u00a0A. Mertler. 2009. Teachers\u2019 assessment knowledge and their perceptions of the impact of classroom assessment professional development. Improving Schools 12 2 (2009) 101\u2013113.","DOI":"10.1177\/1365480209105575"},{"key":"e_1_3_3_3_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16290-9_18"},{"key":"e_1_3_3_3_61_2","doi-asserted-by":"publisher","unstructured":"Nikahat Mulla and Prachi Gharpure. 2023. Automatic question generation: a review of methodologies datasets evaluation metrics and applications. Progress in Artificial Intelligence 12 1 (2023) 1\u201332. 10.1007\/s13748-023-00295-9","DOI":"10.1007\/s13748-023-00295-9"},{"key":"e_1_3_3_3_62_2","doi-asserted-by":"publisher","unstructured":"Geoff Norman. 2010. Likert scales levels of measurement and the \"laws\" of statistics. Adv Health Sci Educ Theory Pract 15 5 (Dec 2010) 625\u2013632. 10.1007\/s10459-010-9222-y","DOI":"10.1007\/s10459-010-9222-y"},{"key":"e_1_3_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.135"},{"key":"e_1_3_3_3_64_2","doi-asserted-by":"crossref","unstructured":"Serafina Pastore and Heidi\u00a0L. Andrade. 2019. Teacher assessment literacy: A three-dimensional model. Teaching and Teacher Education 84 (2019) 128\u2013138.","DOI":"10.1016\/j.tate.2019.05.003"},{"key":"e_1_3_3_3_65_2","doi-asserted-by":"publisher","DOI":"10.17226\/10019"},{"key":"e_1_3_3_3_66_2","unstructured":"PrismJS Contributors. 2012. PrismJS. https:\/\/prismjs.com\/."},{"key":"e_1_3_3_3_67_2","unstructured":"Vatsal Raina and Mark Gales. 2022. Multiple-choice question generation: Towards an automated assessment framework. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2209.11830 (2022)."},{"key":"e_1_3_3_3_68_2","unstructured":"React Syntax Highlighter Contributors. 2016. React Syntax Highlighter. https:\/\/github.com\/react-syntax-highlighter\/react-syntax-highlighter."},{"key":"e_1_3_3_3_69_2","unstructured":"rehype Contributors. 2017. rehype-katex. https:\/\/www.npmjs.com\/package\/rehype-katex."},{"key":"e_1_3_3_3_70_2","unstructured":"remarkjs Contributors. 2016. remark-math. https:\/\/github.com\/remarkjs\/remark-math."},{"key":"e_1_3_3_3_71_2","doi-asserted-by":"crossref","unstructured":"Ana Remesal. 2011. Primary and secondary teachers\u2019 conceptions of assessment: A qualitative study. Teaching and Teacher Education 27 2 (2011) 472\u2013482. 10.1016\/j.tate.2010.09.017.","DOI":"10.1016\/j.tate.2010.09.017"},{"key":"e_1_3_3_3_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714051"},{"key":"e_1_3_3_3_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3641899"},{"key":"e_1_3_3_3_74_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-93567-1_9"},{"key":"e_1_3_3_3_75_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86436-1_22"},{"key":"e_1_3_3_3_76_2","unstructured":"Richard\u00a0J Stiggins. 1988. Revitalizing classroom assessment: The highest instructional priority. The Phi Delta Kappan 69 5 (1988) 363\u2013368. https:\/\/www.jstor.org\/stable\/20403636."},{"key":"e_1_3_3_3_77_2","doi-asserted-by":"crossref","unstructured":"Richard\u00a0J. Stiggins. 2001. The Unfulfilled Promise of Classroom Assessment. Educational Measurement: Issues and Practice 20 3 (2001) 5\u201315.","DOI":"10.1111\/j.1745-3992.2001.tb00065.x"},{"key":"e_1_3_3_3_78_2","doi-asserted-by":"crossref","unstructured":"Richard\u00a0J. Stiggins Nancy\u00a0F. Conklin and Nancy\u00a0J. Bridgeford. 1986. Classroom assessment: A key to effective education. Educational Measurement: Issues and Practice 5 2 (1986) 5\u201317. 10.1111\/j.1745-3992.1986.tb00473.x.","DOI":"10.1111\/j.1745-3992.1986.tb00473.x"},{"key":"e_1_3_3_3_79_2","doi-asserted-by":"publisher","unstructured":"John\u00a0M. Stonehouse and Guy\u00a0J. Forrester. 1998. Robustness of the t and U tests under combined assumption violations. Journal of Applied Statistics 25 1 (1998) 63\u201374. arXiv:10.1080\/02664769823304","DOI":"10.1080\/02664769823304"},{"key":"e_1_3_3_3_80_2","doi-asserted-by":"publisher","DOI":"10.4324\/9780203930939"},{"key":"e_1_3_3_3_81_2","doi-asserted-by":"publisher","unstructured":"Zachari Swiecki Hassan Khosravi Guanliang Chen Roberto Martinez-Maldonado Jason\u00a0M. Lodge Sandra Milligan Neil Selwyn and Dragan Ga\u0161evi\u0107. 2022. Assessment in the age of artificial intelligence. Computers and Education: Artificial Intelligence 3 (2022) 100075. 10.1016\/j.caeai.2022.100075","DOI":"10.1016\/j.caeai.2022.100075"},{"key":"e_1_3_3_3_82_2","doi-asserted-by":"crossref","unstructured":"Maddalena Taras. 2009. Summative assessment: The missing link for formative assessment. Journal of Further and Higher Education 33 1 (2009) 57\u201369. 10.1080\/03098770802638671.","DOI":"10.1080\/03098770802638671"},{"key":"e_1_3_3_3_83_2","doi-asserted-by":"publisher","unstructured":"Marie Tarrant Aimee Knierim Sasha\u00a0K. Hayes and James Ware. 2006. The frequency of item writing flaws in multiple-choice questions used in high stakes nursing assessments. Nurse Education Today 26 8 (2006) 662\u2013671. 10.1016\/j.nedt.2006.07.006","DOI":"10.1016\/j.nedt.2006.07.006"},{"key":"e_1_3_3_3_84_2","unstructured":"Robin\u00a0D Tierney. 2012. Fairness in classroom assessment. SAGE handbook of research on classroom assessment (2012) 125\u2013145."},{"key":"e_1_3_3_3_85_2","doi-asserted-by":"publisher","unstructured":"Luu\u00a0Anh Tuan Darsh Shah and Regina Barzilay. 2020. Capturing Greater Context for Question Generation. Proceedings of the AAAI Conference on Artificial Intelligence 34 05 (2020) 9065\u20139072. 10.1609\/aaai.v34i05.6440","DOI":"10.1609\/aaai.v34i05.6440"},{"key":"e_1_3_3_3_86_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.bea-1.10"},{"key":"e_1_3_3_3_87_2","doi-asserted-by":"publisher","unstructured":"Veronica Villarroel Susan Bloxham Daniela Bruna Carola Bruna and Constanza Herrera-Seda. 2018. Authentic Assessment: Creating A Blueprint for Course Design. Assessment & Evaluation in Higher Education 43 5 (2018) 840\u2013854. 10.1080\/02602938.2017.1412396","DOI":"10.1080\/02602938.2017.1412396"},{"key":"e_1_3_3_3_88_2","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755141"},{"key":"e_1_3_3_3_89_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.22"},{"key":"e_1_3_3_3_90_2","doi-asserted-by":"publisher","DOI":"10.1145\/3231644.3231654"},{"key":"e_1_3_3_3_91_2","unstructured":"WestEd. 2025. The Next Generation Science Standards. https:\/\/www.nextgenscience.org\/."},{"key":"e_1_3_3_3_92_2","doi-asserted-by":"publisher","unstructured":"Nico Willert and Jonathan Thiemann. 2024. Template-Based Generator for Single-Choice Questions. Technology Knowledge and Learning 29 1 (2024) 355\u2013370. 10.1007\/s10758-023-09659-5","DOI":"10.1007\/s10758-023-09659-5"},{"key":"e_1_3_3_3_93_2","doi-asserted-by":"publisher","unstructured":"Chris Woolston. 2015. Psychology journal bans P values. Nature 519 7541 (2015) 9\u20139. 10.1038\/519009f","DOI":"10.1038\/519009f"},{"key":"e_1_3_3_3_94_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.228"},{"key":"e_1_3_3_3_95_2","doi-asserted-by":"publisher","unstructured":"Yueting Xu and Gavin\u00a0T.L. Brown. 2016. Teacher assessment literacy in practice: A reconceptualization. Teaching and Teacher Education 58 (2016) 149\u2013162. 10.1016\/j.tate.2016.05.010","DOI":"10.1016\/j.tate.2016.05.010"},{"key":"e_1_3_3_3_96_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676357"},{"key":"e_1_3_3_3_97_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732176"},{"key":"e_1_3_3_3_98_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713190"}],"event":{"name":"CHI 2026: CHI Conference on Human Factors in Computing Systems","location":"Barcelona Spain","acronym":"CHI '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772318.3790418","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T06:01:35Z","timestamp":1782367295000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772318.3790418"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":97,"alternative-id":["10.1145\/3772318.3790418","10.1145\/3772318"],"URL":"https:\/\/doi.org\/10.1145\/3772318.3790418","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-04-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}