Author

Johan Hallberg Szabadváry

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2026

Information-Geometric Blind Spots of Conformal Test Martingales

Conformal test martingales (CTMs) are e-processes for sequentially testing exchangeability via p-values produced by a conformity function $A$. However, any distribution shift that preserves the push-forward $P\circ A^{-1}$ leaves the p-value distribution invariant, rendering it invisible to every CTM based on $A$. We f...

Johan Hallberg Szabadváry · 0 citations

#artificial intelligence Preprint Oct 2024

When Explanations Compete: Policy-Aware Selection Under Uncertainty

A framework for applying uncertainty-aware explanation policies to a fixed set of generated explanations that allows applications to compare and prioritise explanations according to their intended use is presented.

Helena Löfström, Tuwe Löfström, Johan Hallberg Szabadváry · 2 citations