pith. sign in

arxiv: 2007.02924 · v2 · pith:RBGTRZSTnew · submitted 2020-07-06 · 💻 cs.AI · cs.LG· cs.LO· stat.ML

INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving

classification 💻 cs.AI cs.LGcs.LOstat.ML
keywords provingtheoremgeneralizationbenchmarktheoremsagentsevaluateinequality
0
0 comments X
read the original abstract

In learning-assisted theorem proving, one of the most critical challenges is to generalize to theorems unlike those seen at training time. In this paper, we introduce INT, an INequality Theorem proving benchmark, specifically designed to test agents' generalization ability. INT is based on a procedure for generating theorems and proofs; this procedure's knobs allow us to measure 6 different types of generalization, each reflecting a distinct challenge characteristic to automated theorem proving. In addition, unlike prior benchmarks for learning-assisted theorem proving, INT provides a lightweight and user-friendly theorem proving environment with fast simulations, conducive to performing learning-based and search-based research. We introduce learning-based baselines and evaluate them across 6 dimensions of generalization with the benchmark. We then evaluate the same agents augmented with Monte Carlo Tree Search (MCTS) at test time, and show that MCTS can help to prove new theorems.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Generative Language Modeling for Automated Theorem Proving

    cs.LG 2020-09 unverdicted novelty 8.0

    GPT-f, a transformer-based prover for Metamath, generated new short proofs that were accepted into the main library—the first such contribution from a deep-learning system.