# Wentao Che 2026: 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. 7 records on Mysteries Department cite it. arXiv 2606.22608, submitted 21 June 2026, not yet…

Source: https://mysteriesdept.com/sources/SRC0DEDGCC49XMN/automated-sign-detection-across-the-electronic-babylonian  
Publisher: Mysteries Department  
Licence: CC BY 4.0 (credit Mysteries Department and link the page)  

---

[Sources](https://mysteriesdept.com/sources)[Unread cuneiform: half a million tablets and the limits of Sumerian](https://mysteriesdept.com/mysteries/unread-cuneiform)Wentao Che 2026

**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.

**Unread cuneiform: half a million tablets and the limits of Sumerian** Article0

## 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arXiv 2606.22608, submitted 21 June 2026, not yet peer reviewed.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.

## Cited by on this site 7 records

[A 2026 pipeline links detected signs to text structure by n-gram similarity across 87,668 eBL fragments, the…](https://mysteriesdept.com/mysteries/unread-cuneiform/evidence/EVD0DEEAZT9E1VT/a-2026-pipeline-links-detected-signs-to-text-structure-by-n)

Evidence

EVD

[No blind held-out test of a photograph-to-translation pipeline on unpublished tablets has been published, so the…](https://mysteriesdept.com/mysteries/unread-cuneiform/evidence/EVD0DEDY64BCDSS/no-blind-held-out-test-of-a-photograph-to-translation)

Evidence

EVD

[The 2026 eBL-wide detector reports relative gains over prior work but no absolute sign accuracy, and its authors note…](https://mysteriesdept.com/mysteries/unread-cuneiform/evidence/EVD0DEDXPHRKAXK/the-2026-ebl-wide-detector-reports-relative-gains-over-prior)

Evidence

EVD

[Che and colleagues run a sign detector over 87,668 eBL fragments, producing 2.9 million sign detections](https://mysteriesdept.com/mysteries/unread-cuneiform/events/EVT0DEDPJRJAWX9/che-and-colleagues-run-a-sign-detector-over-87-668-ebl)

EVT

[Enrique Jiménez](https://mysteriesdept.com/mysteries/unread-cuneiform/people/FIG0DEDNESA3K4W/enrique-jimenez)

FIG

[The unread cuneiform: half a million tablets and the limits of Sumerian](https://mysteriesdept.com/mysteries/unread-cuneiform)

The mystery article

MYS

[Can machines read the cuneiform tablets that no scholar has read?](https://mysteriesdept.com/mysteries/unread-cuneiform/questions/QST0DEDT2BJHV5Z/can-machines-read-the-cuneiform-tablets-that-no-scholar-has)

Question

QST

## 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
```

[Find it at arxiv.org](https://arxiv.org/abs/2606.22608)

Key

**SRC** 0DEDGCC49XMN

Kind

Journal article

Rights

The publisher's

Kept

31 Oct 2026, for editors

Added by

[apollo](https://mysteriesdept.com/u/apollo)

The record

Bibliographic records are CC0. Take this one as CSL-JSON, BibTeX or RIS.

[CSL-JSON](https://mysteriesdept.com/sources/SRC0DEDGCC49XMN/automated-sign-detection-across-the-electronic-babylonian/csl.json)