Automated Feedback Generation for Competition-Level Code

TL;DR

This paper introduces Clef, a data-driven tool that automatically generates feedback for competition-level programming submissions by learning repair patterns from historical data, significantly aiding programmers in debugging their code.

Contribution

Clef is the first tool to automatically generate repairs for competition-level code by learning from historical submission data using a novel merge tree data structure.

Findings

Achieves 42.1% repair accuracy on real-world problems

Repairs 34.1% of submissions from programmers who never solved the problem

Introduces merge trees to encode large and small code changes

Abstract

Competitive programming has become a popular way for programmers to test their skills. Large-scale online programming contests attract millions of experienced programmers to compete against each other. Competition-level programming problems are challenging in nature, and participants often fail to solve the problem on their first attempt. Some online platforms for competitive programming allow programmers to practice on competition-level problems as well, and the standard feedback for an incorrect practice submission is the first test case that the submission fails. Often, the failed test case does not provide programmers with enough information to resolve the errors in their code, and they abandon the problem after several more unsuccessful attempts. We present Clef, the first data-driven tool that can generate feedback on competition-level code automatically by repairing programmers' incorrect submissions. The key development is that Clef can learn how to generate repairs for incorrect submissions by examining the repairs that other programmers made to their own submissions over time. Since the differences between an incorrect program and a correct program for the same task may be significant, we introduce a new data structure, merge trees, to capture the changes between submissions. Merge trees are versatile: they can encode both large algorithm-level redesigns and small statement-level alterations. Clef applies the patterns it learns from a database of submissions to generate repairs for new submissions outside the database. We evaluated Clef on six real-world problems from Codeforces, the world's largest platform for competitive programming. Clef achieves 42.1% accuracy in repairing programmers' incorrect submissions. Even when given incorrect submissions from programmers who never found the solution to a problem on their own, Clef repairs the users' programs 34.1% of the time.