{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:49:14Z","timestamp":1777873754545,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737436","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T21:04:26Z","timestamp":1754255066000},"page":"5459-5469","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["MathWriting: A Dataset For Handwritten Mathematical Expression Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8845-1751","authenticated-orcid":false,"given":"Philippe","family":"Gervais","sequence":"first","affiliation":[{"name":"Inceptive, Bern, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6313-5818","authenticated-orcid":false,"given":"Anastasiia","family":"Fadeeva","sequence":"additional","affiliation":[{"name":"Google DeepMind, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8361-2025","authenticated-orcid":false,"given":"Andrii","family":"Maksai","sequence":"additional","affiliation":[{"name":"Google DeepMind, Zurich, Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"[n.d.] Aida calculus math handwriting recognition dataset. https:\/\/www.kaggle.com\/datasets\/aidapearson\/ocr-data. ()."},{"key":"e_1_3_2_2_2_1","unstructured":"Cem Anil et al. 2022. Exploring length generalization in large language models. (2022). arXiv: 2207.04901 [cs.CL]."},{"key":"e_1_3_2_2_3_1","volume-title":"Retrieved","year":"2023","unstructured":"Apple. 2023. Solve math with math notes in calculator on iphone. Retrieved Feb. 23, 2025 from https:\/\/support.apple.com\/guide\/iphone\/solve-math-withmath-notes-iph46efa613a\/ios."},{"key":"e_1_3_2_2_4_1","unstructured":"Lucas Beyer et al. 2024. Paligemma: a versatile 3b vlm for transfer. (2024). https:\/\/arxiv.org\/abs\/2407.07726 arXiv: 2407.07726 [cs.CV]."},{"key":"e_1_3_2_2_5_1","unstructured":"Victor Carbune et al. 2020. Fast multi-language lstm-based online handwriting recognition. (2020). arXiv: 1902.10525 [cs.CL]."},{"key":"e_1_3_2_2_6_1","unstructured":"Xi Chen et al. 2023. Pali: a jointly-scaled multilingual language-image model. (2023). arXiv: 2209.06794 [cs.CV]."},{"key":"e_1_3_2_2_7_1","volume-title":"International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:246996751","author":"Collier Mark","year":"2022","unstructured":"Mark Collier, Rodolphe Jenatton, Efi Kokiopoulou, and Jesse Berent. 2022. Transfer and marginalize: explaining away label noise with privileged information. In International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:246996751."},{"key":"e_1_3_2_2_8_1","volume-title":"Rush","author":"Deng Yuntian","year":"2017","unstructured":"Yuntian Deng, Anssi Kanervisto, Jeffrey Ling, and Alexander M. Rush. 2017. Image-to-markup generation with coarse-to-fine attention. (2017). arXiv: 1609.04938 [cs.CV]."},{"key":"e_1_3_2_2_9_1","unstructured":"[n. d.] Detexify data. https:\/\/github.com\/kirel\/detexify-data. ()."},{"key":"e_1_3_2_2_10_1","unstructured":"Anastasiia Fadeeva Philippe Schlattner Andrii Maksai Mark Collier Efi Kokiopoulou Jesse Berent and Claudiu Musat. 2024. Representing online handwriting for recognition in large vision-language models. (2024). arXiv: 2402.15307 [cs.CV]."},{"key":"e_1_3_2_2_11_1","unstructured":"Gemma Team. 2024. Gemma: open models based on gemini research and technology. (2024). https:\/\/arxiv.org\/abs\/2403.08295 arXiv: 2403 . 08295 [cs.CL]."},{"key":"e_1_3_2_2_12_1","volume-title":"Retrieved","author":"Cloud Google","year":"2023","unstructured":"Google Cloud. 2023. Detect handwriting in image. Retrieved Jan. 31, 2024 from https:\/\/cloud.google.com\/document- ai\/docs\/enterprise- documentocr#ocr_add_ons."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.137"},{"key":"e_1_3_2_2_15_1","volume-title":"How to improve accuracy (Model on TrOCR). Version 1.0. (Mar","year":"2022","unstructured":"2022. How to improve accuracy (Model on TrOCR). Version 1.0. (Mar. 2022). https:\/\/github.com\/huggingface\/transformers\/issues\/16458."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1815330.1815343"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Dmitrijs Kass and Ekta Vats. 2022. Attentionhtr: handwritten text recognition based on attention encoder-decoder networks. (2022). arXiv: 2201.09390 [cs.CV].","DOI":"10.1007\/978-3-031-06555-2_34"},{"key":"e_1_3_2_2_18_1","unstructured":"Daniel Keysers et al. 2020. Measuring compositional generalization: a comprehensive method on realistic data. (2020). arXiv: 1912.09713 [cs.LG]."},{"key":"e_1_3_2_2_19_1","unstructured":"Minghao Li Tengchao Lv Jingye Chen Lei Cui Yijuan Lu Dinei Florencio Cha Zhang Zhoujun Li and Furu Wei. 2022. Trocr: transformer-based optical character recognition with pre-trained models. (2022). https:\/\/arxiv.org\/abs\/2109.10282 arXiv: 2109.10282 [cs.CL]."},{"key":"e_1_3_2_2_20_1","volume-title":"ICDAR'05","author":"Liwicki M.","unstructured":"M. Liwicki and H. Bunke. 2005. IAM-OnDB-an on-line english sentence database acquired from handwritten text on a whiteboard. In ICDAR'05. IEEE."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00247"},{"key":"e_1_3_2_2_22_1","volume-title":"Evaluating sequence-to-sequence models for handwritten text recognition. (2019). arXiv","author":"Michael Johannes","year":"1903","unstructured":"Johannes Michael, Roger Labahn, Tobias Gr\u00fcning, and Jochen Z\u00f6llner. 2019. Evaluating sequence-to-sequence models for handwritten text recognition. (2019). arXiv: 1903.07377 [cs.CV]."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-016-0263-5"},{"key":"e_1_3_2_2_24_1","volume-title":"Recognizing long-form speech using streaming end-to-end models. (2019). arXiv","author":"Narayanan Arun","year":"1910","unstructured":"Arun Narayanan, Rohit Prabhavalkar, Chung-Cheng Chiu, David Rybach, Tara N. Sainath, and Trevor Strohman. 2019. Recognizing long-form speech using streaming end-to-end models. (2019). arXiv: 1910.11455 [eess.AS]."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1031"},{"key":"e_1_3_2_2_26_1","unstructured":"George Retsinas Giorgos Sfikas Basilis Gatos and Christophoros Nikou. 2024. Best practices for a handwritten text recognition system. (2024). arXiv: 2404.11339 [cs.CV]."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","unstructured":"Niels Rogge. 2020. Transformers Tutorials''. Version 1.0. (Sept. 2020). doi:10.5281\/zenodo.1234.","DOI":"10.5281\/zenodo.1234"},{"key":"e_1_3_2_2_28_1","volume-title":"Retrieved","author":"Khan Shahrukh","year":"2021","unstructured":"Shahrukh Khan. 2021. Im2latex-100k. Retrieved Feb. 23, 2025 from https:\/\/www.kaggle.com\/datasets\/shahrukhkhan\/im2latex100k."},{"key":"e_1_3_2_2_29_1","volume-title":"2020 IEEE 4th International Conference on Image Processing, Applications and Systems (IPAS), 199-205","author":"Taee May Mowaffaq","year":"2020","unstructured":"May Mowaffaq AL-Taee, Sonia Ben Hassen Neji, and Mondher Frikha. 2020. Handwritten recognition: a survey. 2020 IEEE 4th International Conference on Image Processing, Applications and Systems (IPAS), 199-205. https:\/\/api.semanticscholar.org\/CorpusID:231823977."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41685-9_14"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.650"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.650"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41679-8_33"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00451"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737436","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:18:37Z","timestamp":1777573117000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737436"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":34,"alternative-id":["10.1145\/3711896.3737436","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737436","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}