{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:47:14Z","timestamp":1782546434154,"version":"3.54.5"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032297594","type":"print"},{"value":"9783032297600","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T00:00:00Z","timestamp":1782604800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T00:00:00Z","timestamp":1782604800000},"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\/978-3-032-29760-0_26","type":"book-chapter","created":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:11:42Z","timestamp":1782544302000},"page":"236-244","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Likelihood-Based Diagnosis with\u00a0Generative Models: Confidence-Aware Measurement from\u00a0Student Writing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2900-4939","authenticated-orcid":false,"given":"S. Thomas","family":"Christie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4555-8764","authenticated-orcid":false,"given":"Matthew","family":"Zent","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8295-6705","authenticated-orcid":false,"given":"Markus","family":"Hauru","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8319-5370","authenticated-orcid":false,"given":"Anna N.","family":"Rafferty","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2192-9797","authenticated-orcid":false,"given":"Simon","family":"Woodhead","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,28]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Almond, R.G., Mislevy, R.J., Steinberg, L.S., Yan, D., Williamson, D.M.: Bayesian networks in educational assessment. Springer (2015)","DOI":"10.1007\/978-1-4939-2125-6"},{"key":"26_CR2","unstructured":"Attali, Y., Burstein, J.: Automated essay scoring with e-rater\u00ae v. 2. J. Technol. Learn. Assess. 4(3) (2006)"},{"issue":"1","key":"26_CR3","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1146\/annurev-statistics-041715-033702","volume":"3","author":"L Cai","year":"2016","unstructured":"Cai, L., Choi, K., Hansen, M., Harrell, L.: Item response theory. Ann. Rev. Stat. Appl. 3(1), 297\u2013321 (2016)","journal-title":"Ann. Rev. Stat. Appl."},{"key":"26_CR4","unstructured":"Chu, Y., et al.: Confusion-aware rubric optimization for LLM-based automated grading. arXiv preprint arXiv:2603.00451 (2026)"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Eignor, D.R.: The standards for educational and psychological testing (2013)","DOI":"10.1037\/14047-013"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Gu, J., et\u00a0al.: A survey on LLM-as-a-judge. Innov. 7(6), 101253 (2026)","DOI":"10.1016\/j.xinn.2025.101253"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Impey, C., Wenger, M., Garuda, N., Golchin, S., Stamer, S.: Using large language models for automated grading of student writing about science. IJAIED. 1\u201335 (2025)","DOI":"10.21203\/rs.3.rs-3962175\/v1"},{"key":"26_CR8","unstructured":"Kadavath, S., et\u00a0al.: Language models (mostly) know what they know. arXiv preprint arXiv:2207.05221 (2022)"},{"issue":"4","key":"26_CR9","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1080\/02796015.2013.12087465","volume":"42","author":"M Kane","year":"2013","unstructured":"Kane, M.: The argument-based approach to validation. Sch. Psychol. Rev. 42(4), 448\u2013457 (2013)","journal-title":"Sch. Psychol. Rev."},{"key":"26_CR10","doi-asserted-by":"publisher","unstructured":"Min, S., Lewis, M., Hajishirzi, H., Zettlemoyer, L.: Noisy channel language model prompting for few-shot text classification. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 5316\u20135330. Association for Computational Linguistics, Dublin, Ireland (2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.365","DOI":"10.18653\/v1\/2022.acl-long.365"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Mohler, M., Mihalcea, R.: Text-to-text semantic similarity for automatic short answer grading. In: Proceedings of the 12th Conference of the European Chapter of the ACL (EACL 2009), pp. 567\u2013575 (2009)","DOI":"10.3115\/1609067.1609130"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Morris, W., Holmes, L., Choi, J.S., Crossley, S.: Automated scoring of constructed response items in math assessment using large language models. IJAIED 35(2), 559\u2013586 (2025)","DOI":"10.1007\/s40593-024-00418-w"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Ohi, M., Kaneko, M., Koike, R., Loem, M., Okazaki, N.: Likelihood-based mitigation of evaluation bias in large language models. In: Ku, L.W., Martins, A., Srikumar, V. (eds.) ACL 2024, pp. 3237\u20133245. Association for Computational Linguistics, Bangkok, Thailand (2024)","DOI":"10.18653\/v1\/2024.findings-acl.193"},{"issue":"7995","key":"26_CR14","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1038\/s41586-023-06924-6","volume":"625","author":"B Romera-Paredes","year":"2024","unstructured":"Romera-Paredes, B., et al.: Mathematical discoveries from program search with large language models. Nature 625(7995), 468\u2013475 (2024)","journal-title":"Nature"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Sung, C., Dhamecha, T.I., Mukhi, N.: Improving short answer grading using transformer-based pre-training. In: International Conference on Artificial Intelligence in Education, pp. 469\u2013481. Springer (2019)","DOI":"10.1007\/978-3-030-23204-7_39"},{"issue":"1","key":"26_CR16","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1111\/j.1745-3992.2011.00223.x","volume":"31","author":"DM Williamson","year":"2012","unstructured":"Williamson, D.M., Xi, X., Breyer, F.J.: A framework for evaluation and use of automated scoring. Educ. Meas. Issues Pract. 31(1), 2\u201313 (2012)","journal-title":"Educ. Meas. Issues Pract."}],"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\/978-3-032-29760-0_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:11:49Z","timestamp":1782544309000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-29760-0_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,28]]},"ISBN":["9783032297594","9783032297600"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-29760-0_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,28]]},"assertion":[{"value":"28 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that\u00a0are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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"}}]}}