Finding Proofs in Tarskian Geometry

TL;DR

This paper demonstrates the successful use of a theorem prover to automatically find proofs for 212 theorems in Tarskian geometry, including challenging long proofs, by developing a methodology for input preparation and proof checking.

Contribution

The paper introduces a methodology for automated proof discovery and verification in Tarskian geometry, successfully proving all 212 theorems including complex long proofs.

Findings

Automated proofs were found for all 212 theorems in the collection.

Most short proofs (under 40 steps) were derived mechanically without human intervention.

The subformula strategy enabled fully mechanical proofs of some complex theorems.

Abstract

We report on a project to use a theorem prover to find proofs of the theorems in Tarskian geometry. These theorems start with fundamental properties of betweenness, proceed through the derivations of several famous theorems due to Gupta and end with the derivation from Tarski's axioms of Hilbert's 1899 axioms for geometry. They include the four challenge problems left unsolved by Quaife, who two decades ago found some \Otter proofs in Tarskian geometry (solving challenges issued in Wos's 1998 book). There are 212 theorems in this collection. We were able to find \Otter proofs of all these theorems. We developed a methodology for the automated preparation and checking of the input files for those theorems, to ensure that no human error has corrupted the formal development of an entire theory as embodied in two hundred input files and proofs. We distinguish between proofs that were found completely mechanically (without reference to the steps of a book proof) and proofs that were constructed by some technique that involved a human knowing the steps of a book proof. Proofs of length 40--100, roughly speaking, are difficult exercises for a human, and proofs of 100-250 steps belong in a Ph.D. thesis or publication. 29 of the proofs in our collection are longer than 40 steps, and ten are longer than 90 steps. We were able to derive completely mechanically all but 26 of the 183 theorems that have "short" proofs (40 or fewer deduction steps). We found proofs of the rest, as well as the 29 "hard" theorems, using a method that requires consulting the book proof at the outset. Our "subformula strategy" enabled us to prove four of the 29 hard theorems completely mechanically. These are Ph.D. level proofs, of length up to 108.