# CoDocBench: A Dataset for Code-Documentation Alignment in Software Maintenance

arXiv: https://arxiv.org/abs/2502.00519 · HTML: https://mlsanity.com/paper/2502.00519/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 17 references that are in the map.
- First posted on arXiv 1 Feb 2025.

## Builds on (most cited first, 5 of 5)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [CodeSearchNet Challenge: Evaluating the State of Semantic Code Search](https://mlsanity.com/paper/1909.09436/) (2019)
- [AutoCodeRover: Autonomous Program Improvement](https://mlsanity.com/paper/2404.05427/) (2024)
- [Practical Program Repair in the Era of Large Pre-trained Language Models](https://mlsanity.com/paper/2210.14179/) (2022)

## Built on by (most cited first, 5 of 5)

- [Agent READMEs: An Empirical Study of Context Files for Agentic Coding](https://mlsanity.com/paper/2511.12884/) (2025)
- [Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality](https://mlsanity.com/paper/2503.05860/) (2025)
- [HASHIRU: Hierarchical Agent System for Hybrid Intelligent Resource Utilization](https://mlsanity.com/paper/2506.04255/) (2025)
- [Context-Augmented Code Generation Using Programming Knowledge Graphs](https://mlsanity.com/paper/2601.20810/) (2026)
- [DoGBench: Can Agents Meet Expert Standards for User-Facing Documentation?](https://mlsanity.com/paper/2609.39909/) (2026)

## Abstract (arXiv)

One of the central tasks in software maintenance is being able to understand and develop code changes. Thus, given a natural language description of the desired new operation of a function, an agent (human or AI) might be asked to generate the set of edits to that function to implement the desired new operation; likewise, given a set of edits to a function, an agent might be asked to generate a changed description, of that function's new workings. Thus, there is an incentive to train a neural model for change-related tasks. Motivated by this, we offer a new, "natural", large dataset of coupled changes to code and documentation mined from actual high-quality GitHub projects, where each sample represents a single commit where the code and the associated docstring were changed together. We present the methodology for gathering the dataset, and some sample, challenging (but realistic) tasks where our dataset provides opportunities for both learning and evaluation. We find that current models (specifically Llama-3.1 405B, Mixtral 8×22B) do find these maintenance-related tasks challenging.