Metraipolis › archive › dc_09a58ebef889

FRAGMENT: Factorized Graph Representations for Document Generation and Editing via Entity-Aware Transformations — arXiv:2608.18679

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.18679
License (as archived): CC0-1.0
Archived: 2026-10-18T14:06:25.284Z
SHA-256 of the archived text: c20be77d2882d4cb10cae1269107258db52b7d581a264421a595a679814786e8
Stable URL of this page: https://metraipolis.com/documento/dc_09a58ebef889

How to cite

FRAGMENT: Factorized Graph Representations for Document Generation and Editing via Entity-Aware Transformations — arXiv:2608.18679 — arXiv (en), https://arxiv.org/abs/2608.18679 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09a58ebef889 (Metraipolis archive dc_09a58ebef889, sha256 c20be77d2882d4cb10cae1269107258db52b7d581a264421a595a679814786e8)

BibTeX

@misc{dc09a58ebef889,
  title = {FRAGMENT: Factorized Graph Representations for Document Generation and Editing via Entity-Aware Transformations — arXiv:2608.18679},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18679},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09a58ebef889; sha256 c20be77d2882d4cb10cae1269107258db52b7d581a264421a595a679814786e8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18679. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Structured documents such as invoices, forms, reports, and scientific articles derive meaning from the interplay between spatial layout, textual content, and logical structure. Generative models operating at the pixel or token level often struggle to capture these dependencies effectively. We explore FRAGMENT, a generative framework that represents a document as a typed relational graph and factorizes its distribution as p(structure, content) = p(structure) * p(content | structure). The framework consists of two stages. The first stage, the Architect, is a causally masked Transformer conditioned on document category that autoregressively generates the graph topology and typed spatial relations. The second stage, the Builder, is a GATv2-based graph attention network that enriches the graph with normalized bounding boxes, text, and visual style attributes. Both stages define explicit likelihood models, yielding a tractable document-level likelihood that serves as an anomaly score for forgery detection. For controlled editing, a prompt-conditioned extension injects instruction embeddings into the Builder through cross-attention, enabling semantic and entity-aware modifications. We describe training on DocLayNet and fine-tuning on FUNSD and SROIE. Experiments on DocLayNet, FUNSD, and SROIE evaluate FRAGMENT alongside representative autoregressive, layout-only, and graph-based baselines, providing an empirical analysis of the characteristics and trade-offs of the proposed factorized graph generation framework.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-20 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.18679 — 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 2026-10-18T14:00:22.573Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).