Codehacks: A Dataset of Adversarial Tests for Competitive Programming Problems Obtained from Codeforces

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hort, Max, Moonen, Leon
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912301060194304
author Hort, Max
Moonen, Leon
author_facet Hort, Max
Moonen, Leon
contents Software is used in critical applications in our day-to-day life and it is important to ensure its correctness. One popular approach to assess correctness is to evaluate software on tests. If a test fails, it indicates a fault in the software under test; if all tests pass correctly, one may assume that the software is correct. However, the reliability of these results depends on the test suite considered, and there is a risk of false negatives (i.e. software that passes all available tests but contains bugs because some cases are not tested). Therefore, it is important to consider error-inducing test cases when evaluating software. To support data-driven creation of such a test-suite, which is especially of interest for testing software synthesized from large language models, we curate a dataset (Codehacks) of programming problems together with corresponding error-inducing test cases (i.e., "hacks"). This dataset is collected from the wild, in particular, from the Codeforces online judge platform. The dataset comprises 288,617 hacks for 5,578 programming problems, each with a natural language description, as well as the source code for 2,196 submitted solutions to these problems that can be broken with their corresponding hacks. Keywords: competitive programming, language model, dataset
format Preprint
id arxiv_https___arxiv_org_abs_2503_23466
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Codehacks: A Dataset of Adversarial Tests for Competitive Programming Problems Obtained from Codeforces
Hort, Max
Moonen, Leon
Software Engineering
Artificial Intelligence
Computation and Language
Machine Learning
Software is used in critical applications in our day-to-day life and it is important to ensure its correctness. One popular approach to assess correctness is to evaluate software on tests. If a test fails, it indicates a fault in the software under test; if all tests pass correctly, one may assume that the software is correct. However, the reliability of these results depends on the test suite considered, and there is a risk of false negatives (i.e. software that passes all available tests but contains bugs because some cases are not tested). Therefore, it is important to consider error-inducing test cases when evaluating software. To support data-driven creation of such a test-suite, which is especially of interest for testing software synthesized from large language models, we curate a dataset (Codehacks) of programming problems together with corresponding error-inducing test cases (i.e., "hacks"). This dataset is collected from the wild, in particular, from the Codeforces online judge platform. The dataset comprises 288,617 hacks for 5,578 programming problems, each with a natural language description, as well as the source code for 2,196 submitted solutions to these problems that can be broken with their corresponding hacks. Keywords: competitive programming, language model, dataset
title Codehacks: A Dataset of Adversarial Tests for Competitive Programming Problems Obtained from Codeforces
topic Software Engineering
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2503.23466