Metraipolis › archive › dc_f3fe0f2a2b3e

WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing — arXiv:2609.20423

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.20423
License (as archived)
CC0-1.0
Archived
2026-10-10T05:07:57.387Z
SHA-256 of the archived text
98d646fb36b048d4a4860f9d3ddcda299d90d6c40730e756954a80470c58e292
Stable URL of this page
https://metraipolis.com/documento/dc_f3fe0f2a2b3e

How to cite

WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing — arXiv:2609.20423 — arXiv (en), https://arxiv.org/abs/2609.20423 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f3fe0f2a2b3e (Metraipolis archive dc_f3fe0f2a2b3e, sha256 98d646fb36b048d4a4860f9d3ddcda299d90d6c40730e756954a80470c58e292)
BibTeX
@misc{dcf3fe0f2a2b3e,
  title = {WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing — arXiv:2609.20423},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.20423},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f3fe0f2a2b3e; sha256 98d646fb36b048d4a4860f9d3ddcda299d90d6c40730e756954a80470c58e292},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20423. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Document parsing converts document images into structured content and requires reliable performance across diverse layouts and acquisition conditions. Yet training corpora are biased toward common document types and clean digital pages, while expanding coverage alone does not specify how to address a parser's remaining weaknesses. We present WeVisDoc, a two-stage data-centric framework for robust end-to-end document parsing. Stage I broadens semantic, structural, and appearance coverage through heterogeneous data and structure-preserving degradation synthesis. Stage II uses a held-out probe to measure the Stage I parser's residual errors within fixed visual-structural clusters. These diagnostics guide targeted data construction and reallocation of the target-token budget. WeVisDoc-4B achieves an Overall score of 95.38 on OmniDocBench v1.6 and a mean Overall score of 75.54 across the three PureDocBench tracks, ranking first among the compared end-to-end parsers in all four settings. Compared with Stage I, Stage II improves Overall scores for the 2B and 4B models on both benchmarks, with larger gains on the degraded PureDocBench tracks, including a 4.03-point gain for the 4B model on the Real Degraded track.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.20423 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-10T04:26:09.606Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).