
Proof Simplification and Automated Theorem Proving
The proofs first generated by automated theorem provers are far from opt...
read it

Proof Artifact Cotraining for Theorem Proving with Language Models
Labeled data for imitation learning of theorem proving in large librarie...
read it

DeepMath  Deep Sequence Models for Premise Selection
We study the effectiveness of neural sequence models for premise selecti...
read it

Using Automated Theorem Provers for Mistake Diagnosis in the Didactics of Mathematics
The Diproche system, an automated proof checker for natural language pro...
read it

CSPLib: Twenty Years On
In 1999, we introduced CSPLib, a benchmark library for the constraints c...
read it

Towards Finding Longer Proofs
We present a reinforcement learning (RL) based guidance system for autom...
read it

Semantic Parsing of Mathematics by Contextbased Learning from Aligned Corpora and Theorem Proving
We study methods for automated parsing of informal mathematical expressi...
read it
Generative Language Modeling for Automated Theorem Proving
We explore the application of transformerbased language models to automated theorem proving. This work is motivated by the possibility that a major limitation of automated theorem provers compared to humans – the generation of original mathematical terms – might be addressable via generation from language models. We present an automated prover and proof assistant, GPTf, for the Metamath formalization language, and analyze its performance. GPTf found new short proofs that were accepted into the main Metamath library, which is to our knowledge, the first time a deeplearning based system has contributed proofs that were adopted by a formal mathematics community.
READ FULL TEXT
Comments
There are no comments yet.