3 papers
cs.LG2026
The Price of Choice in Selective Prediction
Daniel Cieślak, Andrzej Czyżewski
A selective classifier may be claimed to satisfy a risk-coverage contract if some rule from a predeclared menu (a threshold or a union of score intervals) attains coverage at l…
physics.comp-ph2026
Input-schema identifiability limits in physics-informed surrogates for mechanics-governed flow
Daniel Cieslak, Andrzej Czyzewski
Physics-informed and data-driven surrogates are increasingly used to approximate mechanics-governed flow fields, but the target quantities assigned to such models are not always id…
cs.LG2026
Decision-Aware Evaluation of Physics-Informed Surrogates
Daniel Cieślak, Andrzej Czyżewski
Physics-informed machine learning is often assessed by curve error, although engineering use depends on downstream decisions: ranking candidates, avoiding infeasible designs and li…