# One-Slide Calibration of Pathology Foundation Models

arXiv: https://arxiv.org/abs/2610.08944 · HTML: https://mlsanity.com/paper/2610.08944/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 20 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 7 of 7)

- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [SCORPION: Addressing Scanner-Induced Variability in Histopathology](https://mlsanity.com/paper/2507.20907/) (2025)
- [The PAR dataset: Prostate biopsy whole slide images from an underrepresented Middle Eastern population](https://mlsanity.com/paper/2512.03854/) (2025)
- [Deep Learning From Routine Histology Improves Risk Stratification for Biochemical Recurrence in Prostate Cancer](https://mlsanity.com/paper/2603.14187/) (2026)
- [Towards Robust Foundation Models for Digital Pathology](https://mlsanity.com/paper/2507.17845/) (2025)
- [Domain Generalization of Pathological Image Segmentation by Patch-Level and WSI-Level Contrastive Learning](https://mlsanity.com/paper/2508.07539/) (2025)
- [DistillPath: An Efficient 22M Distilled Pathology Encoder Approaching Large Foundation Model Performance](https://mlsanity.com/paper/2608.17872/) (2026)

## Abstract (arXiv)

Scanner variation changes how pathology foundation models represent the same tissue. We introduce SlideRuler, which uses regions within a slide as internal controls to estimate and correct acquisition-induced shifts in other regions. A transfer map learned from paired rescans enables calibration from a single scan at inference while keeping the foundation model fixed. Across two encoders and five SCORPION scanners, learned transfer reduces mean target-to-source embedding distance by 16.3-38.5% relative to raw embeddings. Comparisons with unrelated same-scanner controls reveal a positive same-slide contribution across all four evaluation settings, including scanner holdout. A source-anchored variant reduces source-feature displacement by 47.7-83.6% relative to learned transfer while retaining most of its alignment gain. By drawing calibration information from the slide itself, SlideRuler offers a path toward more consistent use of frozen pathology models across imaging systems.