Reproduce “Discovering quantum phenomena with Interpretable Machine Learning” 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
Paulin de Schoulepnikoff, Hendrik Poulsen Nautrup, Hans J. Briegel, Gorka Muñoz-Gil
The authors pair a probabilistic variational autoencoder with symbolic regression to turn quantum measurements into interpretable descriptors. The autoencoder models measurement distributions in a latent representation, while symbolic regression separates a selected region using compact expressions. On experimental Rydberg snapshots, the method identifies corner-first ordering within a known edge-ordered region, supporting a pattern rather than proving a new thermodynamic phase.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.