0
Automated sign detection across the Electronic Babylonian Library: A large-scale dataset and end-to-end cuneiform OCR pipeline
Wentao Che, Esteban Garcés Arias, Asim Niaz et al., 2026.
What it's used for here
arXiv 2606.22608, submitted 21 June 2026, not yet peer reviewed. Deformable DETR sign detector at 173 and 106 sign classes, lines grouped and linked to transliterations by n-gram similarity; applied to 87,668 eBL tablet fragments giving about 2.9 million sign detections; authors note sensitivity to damage and layout and the absence of linguistic priors. Used for the current state of cuneiform OCR at scale.
Our copy
Research copy, for editors and curators. The work is the publisher's, so readers are sent to it. We keep this copy so the citation can be checked if the page changes or goes.
arxiv.org · fetched 31 Oct 2026
Loading…
Cited by on this site 7 records
The unread cuneiform: half a million tablets and the limits of Sumerian
MYSThe mystery article
Cite it
Wentao Che, Esteban Garcés Arias, Asim Niaz, Andreas Bender, & Enrique Jiménez (2026). Automated sign detection across the Electronic Babylonian Library: A large-scale dataset and end-to-end cuneiform OCR pipeline. https://arxiv.org/abs/2606.22608
@article{che2026signdetection,
author = {Wentao Che} and {Esteban Garcés Arias} and {Asim Niaz} and {Andreas Bender} and {Enrique Jiménez},
title = {Automated sign detection across the Electronic Babylonian Library: A large-scale dataset and end-to-end cuneiform OCR pipeline},
year = {2026},
url = {https://arxiv.org/abs/2606.22608}
}TY - GEN TI - Automated sign detection across the Electronic Babylonian Library: A large-scale dataset and end-to-end cuneiform OCR pipeline AU - Wentao Che AU - Esteban Garcés Arias AU - Asim Niaz AU - Andreas Bender AU - Enrique Jiménez PY - 2026 UR - https://arxiv.org/abs/2606.22608 ER -
et al.. “Automated sign detection across the Electronic Babylonian Library: A large-scale dataset and end-to-end cuneiform OCR pipeline.” 2026.