Stefanie Speidel

SEP 4, 2026 · PREPRINT

When Genomic Masking Priors Fail to Transfer: Strong Variant Prediction, Weak Functional Generation

arXiv

A single-center machine learning model development study with mixed results on surrogate endpoints (variant prediction AUROC, functional inpainting), no clinical validation, and failure of the core hypothesis that entropy guidance improves function, warranting independent replication before clinical application.

AUG 18, 2026 · PREPRINT

Looking Beyond the Scale: Do Surgical Skill Models Learn Transferable Representations Across Assessment Rubrics?

arXiv

An unreviewed exploratory analysis of cross-domain transfer in surgical skill assessment models, using controlled experiments to probe representation learning but without clinical validation or a definitive answer to its central question.