
HoCHC: a Refutationallycomplete and Semanticallyinvariant System of Higherorder Logic Modulo Theories
We present a simple resolution proof system for higherorder constrained...
read it

Holophrasm: a neural Automated Theorem Prover for higherorder logic
I propose a system for Automated Theorem Proving in higher order logic u...
read it

GRUNGE: A Grand Unified ATP Challenge
This paper describes a large set of related theorem proving problems obt...
read it

Premise Selection for Theorem Proving by Deep Graph Embedding
We propose a deep learningbased approach to the problem of premise sele...
read it

HolStep: A Machine Learning Dataset for Higherorder Logic Theorem Proving
Large computerunderstandable proofs consist of millions of intermediate...
read it

An Experimental Study of Formula Embeddings for Automated Theorem Proving in FirstOrder Logic
Automated theorem proving in firstorder logic is an active research are...
read it

Theorem Proving Based on Semantics of DNA Strand Graph
Because of several technological limitations of traditional silicon base...
read it
Graph Representations for HigherOrder Logic and Theorem Proving
This paper presents the first use of graph neural networks (GNNs) for higherorder proof search and demonstrates that GNNs can improve upon stateoftheart results in this domain. Interactive, higherorder theorem provers allow for the formalization of most mathematical theories and have been shown to pose a significant challenge for deep learning. Higherorder logic is highly expressive and, even though it is wellstructured with a clearly defined grammar and semantics, there still remains no wellestablished method to convert formulas into graphbased representations. In this paper, we consider several graphical representations of higherorder logic and evaluate them against the HOList benchmark for higherorder theorem proving.
READ FULL TEXT
Comments
There are no comments yet.