Ground Truth for PaganTibet Layout Recognition

This dataset contains TEI XML files encoding the layout structure of Tibetan manuscripts, produced as part of the PaganTibet project by Rachael M. Griffiths. These were exported from Transkribus, using their default TEI XML export format. The files record zone coordinates for text regions and individual lines but do not include transcription text. Note: most source images consist of two manuscript pages photographed together and treated as a single facsimile unit, so coordinates often reflect a two-page layout.

Accompanying images and full eTexts will be made available through the BDRC's BUDA platform.PaganTibet is an ERC-funded Advanced Grant project (ERC, PaganTibet, 101097364) led by Professor Charles Ramble (PI) in the Horizon Europe framework, hosted by the École Pratique des Hautes Études (EPHE), PSL in Paris. Ⓒ Rachael M. Griffiths (PaganTibet member), March 2026. This dataset is licensed under CC BY NC-SA 4.0.