SciEGQA: A Dataset for Scientific Evidence-Grounded Question Answering and Reasoning

ArXi:2511.15090v2 Announce Type: replace-cross Scientific documents contain complex multimodal structures, which makes evidence localization and scientific reasoning in Document Visual Question Answering particularly challenging. However, most existing benchmarks evaluate models only at the page level without explicitly annotating the evidence regions that the answer, which limits both interpretability and the reliability of evaluation. To address this limitation, we