Metraipolis › archive › dc_4e82ab85b6f3
When Can Text Replace Vision? Structural Bottlenecks in Diagram Reasoning — arXiv:2609.39142
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39142
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T14:45:55.337Z
- SHA-256 of the archived text
19c6aabeb70849a98db2214a75ad4da663c9ddd473b5ae4c1f4eed8055c33c6c- Stable URL of this page
https://metraipolis.com/documento/dc_4e82ab85b6f3
How to cite
When Can Text Replace Vision? Structural Bottlenecks in Diagram Reasoning — arXiv:2609.39142 — arXiv (en), https://arxiv.org/abs/2609.39142 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e82ab85b6f3 (Metraipolis archive dc_4e82ab85b6f3, sha256 19c6aabeb70849a98db2214a75ad4da663c9ddd473b5ae4c1f4eed8055c33c6c)
BibTeX
@misc{dc4e82ab85b6f3,
title = {When Can Text Replace Vision? Structural Bottlenecks in Diagram Reasoning — arXiv:2609.39142},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39142},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e82ab85b6f3; sha256 19c6aabeb70849a98db2214a75ad4da663c9ddd473b5ae4c1f4eed8055c33c6c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39142. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Can structured text replace vision for diagram reasoning? A wrong answer after textualization can arise because the representation omits information the question needs, or because the solver fails to use information that is present. We introduce a diagnostic protocol to distinguish these explanations. Using the same solver model and generation settings, we compare three input conditions: the original image, question-blind structure extracted by a vision-language model, or gold structure derived from the diagram source. Validity-triggered recovery tests truncation and schema failure, question-relevant fidelity measures preservation of answer-critical structure, and matched edge interventions test the effect of error location. On a reserved holdout of 240 public FlowGen diagrams, evaluated under a frozen protocol, gold structure reaches 87% accuracy while direct vision and learned text both remain below 30%. The aggregate comparison includes source-derived relation labels that may not be printed in the image and uses different learned and gold graph encodings, so it does not isolate extraction error alone. Retrying only invalid extractions makes nearly every public representation schema-valid yet leaves accuracy essentially unchanged. The public learned-text deficit relative to gold more than doubles with structural difficulty. Question-relevant topology predicts correctness better than whole-graph topology. In an exposed intervention study, a single answer-relevant edge edit reduces the primary solver's original-answer accuracy to near zero, while matched irrelevant edits largely preserve it. Supplied structure requires fewer solving tokens than vision, but learned acquisition removes this advantage at single use. These comparisons motivate evaluating acquired text by the answer-relevant evidence it preserves and by the solver's ability to use that representation. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.39142 — 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 2026-10-07T14:19:00.694Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).