Metraipolis › archive › dc_340dc44e441b

SlideBank: A Persistent Hierarchical Evidence Bank for Consistent Whole-Slide Reasoning — arXiv:2609.00342

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.00342
License (as archived): CC0-1.0
Archived: 2026-10-17T06:31:48.593Z
SHA-256 of the archived text: 951e22211e656bf25c542dbbe1aa4cc3de384ea6d8188d9b85f904a8cb4c8ef9
Stable URL of this page: https://metraipolis.com/documento/dc_340dc44e441b

How to cite

SlideBank: A Persistent Hierarchical Evidence Bank for Consistent Whole-Slide Reasoning — arXiv:2609.00342 — arXiv (en), https://arxiv.org/abs/2609.00342 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_340dc44e441b (Metraipolis archive dc_340dc44e441b, sha256 951e22211e656bf25c542dbbe1aa4cc3de384ea6d8188d9b85f904a8cb4c8ef9)

BibTeX

@misc{dc340dc44e441b,
  title = {SlideBank: A Persistent Hierarchical Evidence Bank for Consistent Whole-Slide Reasoning — arXiv:2609.00342},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00342},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_340dc44e441b; sha256 951e22211e656bf25c542dbbe1aa4cc3de384ea6d8188d9b85f904a8cb4c8ef9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00342. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Whole-slide images (WSIs) are challenging for vision-language reasoning because diagnostically relevant morphology is sparse, heterogeneous, and distributed across gigapixel-scale images and multiple spatial resolutions. Existing WSI models and pathology agents can aggregate slide features or actively acquire evidence, but the information retained after exploration is often difficult to access semantically while preserving its connection to the original visual evidence. We introduce SlideBank, a training-free framework that represents each WSI as a persistent, concept-indexed, and spatially grounded evidence bank. SlideBank performs question-independent coarse-to-fine exploration to identify informative regions and multi-scale views, converts them into explicit morphological observations, and grounds pathology signals to their supporting patches and WSI coordinates. At inference time, questions are routed to relevant signals and evidence scales, and the linked global, regional, and patch evidence is integrated through confidence-based cross-level consensus. Experiments on WSI-VQA and SlideBench-BCNB show that with Patho-R1, SlideBank reaches 52.77% on WSI-VQA and with Quilt-LLaVA, it reaches 50.92% average accuracy on SlideBench-BCNB, while structured signal-guided retrieval consistently outperforms random evidence sampling. Reusing the same bank across repeated queries further achieves over 99% rephrasing consistency and substantially reduces amortized inference cost through persistent evidence reuse.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.00342 — 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 2026-10-17T06:15:12.585Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).