Reproduce “An end-to-end framework for uncertainty-aware validation of generative models” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Giada Badaracco, Sean Benevedes, Christina Reissel, Philip Harris, Gaia Grosso
SIGMA carries estimated fit uncertainty into goodness-of-fit tests, allowing the reference model to vary rather than treating its fitted parameters as exact. In QCD simulations, tests retain calibration to about one-tenth the training-set size with Gaussian calibration and one-fifth with bootstrap calibration for larger mixture models. This does not cover model bias or guarantee validity beyond those settings.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.