Metraipolis › archive › dc_eb17e4767e1f

InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations — arXiv:2609.01383

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.01383
License (as archived)
CC0-1.0
Archived
2026-10-17T06:41:38.519Z
SHA-256 of the archived text
febc04d098eee7e019e6b39957f2a4c06810491ff9b8a24f86ae9451fe5b42fb
Stable URL of this page
https://metraipolis.com/documento/dc_eb17e4767e1f

How to cite

InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations — arXiv:2609.01383 — arXiv (en), https://arxiv.org/abs/2609.01383 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb17e4767e1f (Metraipolis archive dc_eb17e4767e1f, sha256 febc04d098eee7e019e6b39957f2a4c06810491ff9b8a24f86ae9451fe5b42fb)
BibTeX
@misc{dceb17e4767e1f,
  title = {InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations — arXiv:2609.01383},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01383},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb17e4767e1f; sha256 febc04d098eee7e019e6b39957f2a4c06810491ff9b8a24f86ae9451fe5b42fb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01383. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision Language Models have demonstrated remarkable proficiency in interpreting static visual artifacts, but modern data analysis is inherently dynamic, requiring the active interrogation of interactive environments. Existing benchmarks are predominantly constrained to static imagery and one-shot question answering and fail to capture the epistemic demands of this domain, where evidence is frequently occluded, distributed across linked views, or conditionally revealed through user agency. In this paper, we introduce InSight, a benchmark for agentic claim verification over interactive visualizations. The dataset consists of 21,349 claims derived from human-authored analytical narratives and grounded in fully interactive web-based environments. Agents must navigate these environments to determine whether a natural language claim is supported, refuted or not verifiable given the available evidence. Unlike traditional evaluations, InSight treats interaction traces as intrinsic proxies for reasoning, enabling a rigorous audit of how models seek and synthesize visual evidence. We evaluate state-of-the-art models, revealing that interactive verification remains a non-trivial challenge. We release InSight at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Computer Vision and Pattern Recognition (cs.CV); Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2609.01383 — 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 2026-10-17T06:33:38.865Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).