Photo: Daniel Berounsky

Outputs

Here we are posting a running record of the various outputs of the PaganTibet project, including publications, conference and poster presentations, and digital tools and models.

Publications

Journal articles, book chapters, conference proceedings

Presentations

Conferences, workshops, posters

Digital outputs

HTR models, Ground Truth, manuals and cheatsheets

Publications

Journal articles

Griffiths, Rachael M. and Marieke Meelen. 2026. “From Large and Complex Manuscript Collections to Searchable eTexts: the Case of PaganTibet.” Revue d’Etudes Tibétaines (forthcoming) (peer-reviewed)

Meelen, Marieke and Rachael M. Griffiths. 2025. “Collaborative Workflows for Handwritten Text Recognition in Under-Resourced Manuscript Collections.“ Journal of Open Humanities Data, no. 11: 54 (2059-481X) (peer reviewed) 10.5334/johd.388https://openhumanitiesdata.metajnl.com/articles/10.5334/johd.388

Meelen, Marieke, Sebastian Nehrdich, and Kurt Keutzer. 2024. “Breakthroughs in Tibetan NLP and Digital Humanities.” Revue d’Etudes Tibétaines 72: 5–25 (1768-2959) (peer reviewed) 10.17863/CAM.110900https://d1i1jdw69xsqx0.cloudfront.net/digitalhimalaya/collections/journals/ret/pdf/ret_72_01.pdf

Punzi, Valentina. 2025. “Fresh Twigs, Drying Blood, and Popped Corn: The Ephemeral Materiality of Eastern Minyag Ritual Objects.” Religions 16, no. 5: 539 (2077-1444) (peer reviewed) 10.3390/rel16050539 https://www.mdpi.com/2077-1444/16/5/539

Naljor Tsering (Naojiucili). 2025. “Rgya nag skag bzlog: The ‘Chinese Way of Repelling Disaster’ or ‘Repelling Chinese Disasters.’” Cahiers d’Extrême-Asie 34. Catastrophe and Prophecy in Tibetan Religious Contexts, edited by Brandon Dotson and Jetsun Deleplanque. (peer-reviewed) https://publications.efeo.fr/fr/livres/1033_cahiers-d-extreme-asie-34-2025 (abstract only available) 

Book chapters

Berounský, Daniel. 2026. “A Myth on the Separation of the Dead from the Living in the Newly Found Ancient Manuscript from the Twin Stūpas (Gansu Province, PRC).” In Recent Research on Tibet: A Festschrift for Guntram Hazod on the Occasion of His 70th Birthday, edited by Per K. Sørensen and Christian Jahoda. Vienna: Austrian Academy of Sciences Press, 581–607. https://doi.org/10.1553/978OEAW50671s581  

Ramble, Charles. 2026. “The Outer Support Arrangement: An Installation for the Worship of Pagan Gods in the Entourage of a Bonpo Tantric Divinity.” In Recent Research on Tibet: A Festschrift for Guntram Hazod on the Occasion of His 70th Birthday, edited by Per K. Sørensen and Christian Jahoda. Vienna: Austrian Academy of Sciences Press, 449–485. https://doi.org/10.1553/978OEAW50671s449

Books

Ramble, Charles, Naljor Tsering, Agnieszka Helman-Ważny, and Nils Martin. (forthcoming 2026). Tibetan Manuscripts and Rituals of the Royal Bön Priests of Mustang, Nepal: A Codicological and Historical Study (Brill’s Tibetan Studies Library, 57). Leiden: Brill. https://brill.com/display/title/70129

Presentations

Griffiths, Rachael. 2025. “Working Around Unicode Gaps in Tibetan HTR.” OCR/HTR for Under Researched and Under Represented Languages in DH, Vienna, 3-4 Oct 2025. Zenodo. 10.5281/zenodo.17280564. [Presentation]

Griffiths, Rachael M. and Marieke Meelen. 2024. “Uncovering Tibet’s Oldest Religion through AI-enhanced Handwritten Text Recognition.” Cambridge Language Sciences Annual Symposium 2024 (21 Nov. 2024) Cambridge Open Engage. 10.33774/coe-2024-6d77x [Poster]

Griffiths, Rachael M. and Marieke Meelen. 2025. “A multi-stage approach to information extraction and text classification in large untranscribed manuscript collections.” Cambridge Language Sciences Annual Symposium 2025 (27 Nov. 2025) Cambridge Open Engage. 10.33774/coe-2025-kjqqh [Poster]

Griffiths, Rachael M. et al. 2026. “Ten annoying things about digitizing under-resourced and under-represented languages (And what might help fixing them).” Zenodo. 10.5281/zenodo.18232603. [Outcomes of a writing sprint during the workshop OCR/HTR for Under Researched and Under Represented Languages in Digital Humanities held at the Central European University, Vienna, on 3–4 October 2025]

Digital outputs

PaganTibet in repositories, community platforms

Layout:

Layout models (Tibetan Manuscript 1, Tibetan Manuscript 2 & Tibetan Manuscript 3). Transkribus.

Griffiths, Rachael M. 2026. Ground Truth for PaganTibet Layout Recognition (TEI XML files). Zenodo. https://doi.org/10.5281/zenodo.19205597

HTR:

HTR models: Ume1Ume2Ume3Ume4 & Ume5. (Transkribus Model ID: 443525) Transkribus

Ground Truth for HTR models (Ume1 & Ume2). 2025. Griffiths, R.M., Meelen, M., Berounský, D., des Jardins, M., Gurung, K. N., Mulraney, S., Punzi, V., Ramble, C., Szabóová, L., Tsering, N., Tso, K., Chokgyal, S., Gyaltsen, T., Drukgyal, T., Gyatso, T., Lhundup, T., Palsang, T., Rabsal, T., Wangchuk, P., Woeser, T., Woser, S. (2025). [TXT file] Zenodo. 10.5281/zenodo.17275723

Tibetan HTR Postprocessing Script [Python script]. https://github.com/pagantibet/htr/

Meelen, Marieke and Rachael M. Griffiths. 2025. “HTR Input & Correction Manual” [PDF file]. 10.5281/zenodo.17257008

Griffiths, Rachael M. and Marieke Meelen. 2025. “HTR Input & Correction Cheat Sheet: 10 Basic Rules and Protocols for Diplomatic Transcription” [PDF file]. 10.5281/zenodo.17251317

Normalisation:

PaganTibet Normalisation code repository: https://github.com/pagantibet/normalisation?tab=readme-ov-file

Meelen, Marieke and Rachael M. Griffiths. 2026. “Normalisation Manual.” [PDF file] https://zenodo.org/records/18984000

Meelen, Marieke and Rachael M. Griffiths. 2026. “Normalisation Cheat Sheet.” [PDF file] https://doi.org/10.5281/zenodo.18983630

Handwritten Text Recognition - HTR