Programming Puzzles
Abstract
We introduce a new type of programming challenge called programming puzzles, as an objective and comprehensive evaluation of program synthesis, and release an open-source dataset of Python Programming Puzzles (P3). Each puzzle is defined by a short Python program , and the goal is to find an input which makes return True. The puzzles are objective in that each one is specified entirely by the source code of its verifier , so evaluating is all that is needed to test a candidate solution. They do not require an answer key or input/output examples, nor do they depend on natural language understanding. The dataset is comprehensive in that it spans problems of a range of difficulties and domains, ranging from trivial string manipulation problems, to classic programming puzzles (e.g., Tower of Hanoi), to interview/competitive-programming problems (e.g., dynamic programming), to longstanding open problems in algorithms and mathematics (e.g., factoring). We develop baseline enumerative program synthesis, GPT-3 and Codex solvers that are capable of solving puzzles -- even without access to any reference solutions -- by learning from their own past solutions. Codex performs best, solving up to 18% of 397 test problems with a single try and 80% of the problems with 1,000 tries per problem. In a small user study, we find a positive correlation between puzzle-solving performance and coding experience, and between the puzzle difficulty for humans and AI solvers. Therefore, further improvements on P3 could have a significant impact on many program synthesis areas.
Cite
@article{arxiv.2106.05784,
title = {Programming Puzzles},
author = {Tal Schuster and Ashwin Kalyan and Oleksandr Polozov and Adam Tauman Kalai},
journal= {arXiv preprint arXiv:2106.05784},
year = {2021}
}
Comments
NeurIPS 2021 (Datasets and Benchmarks Track). Puzzles repository: https://github.com/microsoft/PythonProgrammingPuzzles