Metraipolis › archive › dc_e6a24bc0ce49
When Does an Image Determine the Answer? Benchmarking Visual Answerability across Charts and Scenes — arXiv:2609.34480
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34480
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:52:09.799Z
- SHA-256 of the archived text
f4d96cd4e7238717788b65eaf09c9715e39a851e8e83e4e06890992e527ea3d5- Stable URL of this page
https://metraipolis.com/documento/dc_e6a24bc0ce49
How to cite
When Does an Image Determine the Answer? Benchmarking Visual Answerability across Charts and Scenes — arXiv:2609.34480 — arXiv (en), https://arxiv.org/abs/2609.34480 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e6a24bc0ce49 (Metraipolis archive dc_e6a24bc0ce49, sha256 f4d96cd4e7238717788b65eaf09c9715e39a851e8e83e4e06890992e527ea3d5)
BibTeX
@misc{dce6a24bc0ce49,
title = {When Does an Image Determine the Answer? Benchmarking Visual Answerability across Charts and Scenes — arXiv:2609.34480},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34480},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e6a24bc0ce49; sha256 f4d96cd4e7238717788b65eaf09c9715e39a851e8e83e4e06890992e527ea3d5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34480. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reliable visual question answering requires correct answers when evidence is sufficient and abstention when it is not. We introduce a benchmark that connects complete-question evaluation with explicit evidence for its labels across PlotQA charts, CLEVR rendered scenes, and GQA photographs. Each question groups original and edited images, presented independently; success requires every supported answer and every required abstention to be correct. For chart missing-information labels, executable witnesses establish that admissible complete charts give different answers but identical pixels after masking. Scene labels follow source programs and edits, with a residual-cue analysis for photographs. Across 72,000 responses from six model configurations, the highest observed complete task success rates are 57.0%, 43.5%, and 33.7%, respectively. On charts, the strongest configuration achieves 96.2% per-view decision accuracy, yet 265 of its 835 groups with every decision correct still contain incorrect answers. Evaluating supported answers and necessary abstentions together exposes failures that answerability decisions alone conceal. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.34480 — 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 2026-10-07T23:29:27.374Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).