Metraipolis › archive › dc_a69acc04535b

ExBind: A Controlled Diagnostic Benchmark for Visual-to-Executable Correspondence — arXiv:2609.01344

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.01344
License (as archived)
CC0-1.0
Archived
2026-10-17T07:13:53.009Z
SHA-256 of the archived text
c7c5f537608d76391033da4b7176bc3c3f0bd07cf61ecc4d86fb705141c59ea1
Stable URL of this page
https://metraipolis.com/documento/dc_a69acc04535b

How to cite

ExBind: A Controlled Diagnostic Benchmark for Visual-to-Executable Correspondence — arXiv:2609.01344 — arXiv (en), https://arxiv.org/abs/2609.01344 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a69acc04535b (Metraipolis archive dc_a69acc04535b, sha256 c7c5f537608d76391033da4b7176bc3c3f0bd07cf61ecc4d86fb705141c59ea1)
BibTeX
@misc{dca69acc04535b,
  title = {ExBind: A Controlled Diagnostic Benchmark for Visual-to-Executable Correspondence — arXiv:2609.01344},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01344},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a69acc04535b; sha256 c7c5f537608d76391033da4b7176bc3c3f0bd07cf61ecc4d86fb705141c59ea1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01344. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal coding and editing systems must map a visible or semantic referent to the exact executable object that can be edited. A wrong reference may select a valid but incorrect DOM node, SVG element, graph endpoint, hierarchy member, or table cell, while final execution success alone does not reveal the source of the failure. ExBind isolates this visual-to-executable correspondence layer as a controlled diagnostic benchmark between semantic localization and action execution. It samples representation-independent latent binding instances and compiles them into SVG, DOM, canvas, tree, graph, and table cases with deterministic mappings to executable references. Models output only a strict reference; the evaluator maps predictions back to latent structure and scores structural constraints without requiring reasoning traces. The release contains a 250-case broad suite, a disjoint 240-case targeted suite, and 50 paired latent groups. Qwen2.5-VL-3B achieves 98.4% candidate validity but 76.4% exact accuracy, while Qwen3-VL-4B achieves 100.0% validity and 98.8% exact accuracy. In the targeted table suite, all Qwen2.5-VL-3B residual errors are valid correct-row/wrong-column selections. Candidate-order perturbations change case-level outcomes while preserving this error pattern. ExBind is designed for controlled diagnosis rather than population-scale ranking or end-to-end editing evaluation. Code and benchmark records are available at this https URL and this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.01344 — 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 2026-10-17T07:00:58.981Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).