Reproduce “Rule-Based Languages for Neurosymbolic AI” 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
Stefania Dumbrava, Efthymia Tsamoura
The authors survey more than 50 rule-based neurosymbolic systems, mapping application needs to choices in semantics, expressiveness, neural integration, and evaluation. Their decision matrix compares six scenarios, while provenance semirings offer a partial way to vary evaluation without rewriting rules. The matrix is a literature synthesis, not a performance experiment, and probabilistic inference remains a scalability bottleneck.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.