Metraipolis › archive › dc_fc7bdd59be5f
Towards Trustworthy Biological Alignment in TabPFN-Probed Pathology Foundation Models — arXiv:2609.29523
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.29523
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T04:19:52.356Z
- SHA-256 of the archived text
1fefd538efe1a1947e64bd1bf16220580364b7e4e23acddc5eb77de2db441446- Stable URL of this page
https://metraipolis.com/documento/dc_fc7bdd59be5f
How to cite
Towards Trustworthy Biological Alignment in TabPFN-Probed Pathology Foundation Models — arXiv:2609.29523 — arXiv (en), https://arxiv.org/abs/2609.29523 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc7bdd59be5f (Metraipolis archive dc_fc7bdd59be5f, sha256 1fefd538efe1a1947e64bd1bf16220580364b7e4e23acddc5eb77de2db441446)
BibTeX
@misc{dcfc7bdd59be5f,
title = {Towards Trustworthy Biological Alignment in TabPFN-Probed Pathology Foundation Models — arXiv:2609.29523},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.29523},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc7bdd59be5f; sha256 1fefd538efe1a1947e64bd1bf16220580364b7e4e23acddc5eb77de2db441446},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29523. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Histology and transcriptomics provide complementary views of tissue biology, capturing spatial morphology and molecular activity, respectively. Pathology foundation models (PFMs) learn rich morphological representations from H&E images, yet strong downstream performance alone does not establish whether these representations encode biologically meaningful and robust molecular information. We present a **training-free framework for auditing biological alignment in frozen PFMs** using spatially paired histology and transcriptomics from HEST-1k, evaluated on **240 samples spanning three organs**. Multiple frozen PFMs are used to extract H&E representations, while gene expression is aggregated into biologically interpretable pathway-level programs. We use TabPFN as a pretrained probe to quantify the extent to which these molecular programs can be decoded from frozen image representations without task-specific gradient updates. Beyond predictive performance, our audit examines whether pathway decodability generalizes across tissue sections, patient groups, and tissue types; whether representations exhibit section-level or other shortcut dependencies; and whether predictions remain stable under small image perturbations and context resampling. This multi-tissue evaluation distinguishes molecular programs that are consistently encoded from those that are tissue-specific, unstable, or shortcut-sensitive. Our framework therefore provides a systematic approach for assessing not only **what biological information pathology foundation models encode, but also how reliably that information persists under clinically relevant sources of variation**. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.MA). Categorie arXiv: Multiagent Systems (cs.MA) ; Quantitative Methods (q-bio.QM). Pagina del lavoro: https://arxiv.org/abs/2609.29523 — 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 2026-10-08T03:50:35.805Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).