[KongchangAI]
BenchmarkProofNetVerif

ProofNetVerif

A test set for evaluating methods that detect equivalence of formal mathematical statements, containing human-adjudicated labels for equivalent and non-equivalent statement pairs.

Timeline (last 90 days)

Oct 26

SemantEq-Eval is a model-free search method that achieves 100% precision and 65.6% recall (based on human-adjudicated labels) on the ProofNetVerif test set.

Unverified50%
Oct 26

BEq+ achieves 95.8% precision and 61.8% recall on the ProofNetVerif test set.

Unverified50%

All Facts (2)

Source Articles