This paper details the reconstruction and execution of the Logic Theorist (LT), considered the first artificial intelligence program, originally created in 1955-1956. The authors built a new IPL-V interpreter in Common Lisp and faithfully reanimated LT from code transcribed from a 1963 RAND technical report. The reanimated LT successfully proved 16 of 23 theorems from Principia Mathematica, consistent with the original system's behavior. This work demonstrates "executable archaeology" as a method for understanding early AI systems, highlighting the challenges and insights gained from reconstructing and running historical code.
This GitHub repository contains a re-implementation of the IPL-V programming language and the Logic Theorist (LT) program. It includes the original code transcribed into a TSV format and converted to Lisp, along with documentation and debugging tools.
The Wikipedia article details the Logic Theorist, created in 1956 by Allen Newell, Herbert A. Simon, and Cliff Shaw. Widely considered the first AI program, it successfully proved 38 of the first 52 theorems in Principia Mathematica, even discovering more elegant proofs than those originally crafted by Russell and Whitehead.
Jeff Shrager has reanimated LT in IPL-V with a new implementation.
