# DR.FIX: Automatically Fixing Data Races at Industry Scale

arXiv: https://arxiv.org/abs/2504.15637 · HTML: https://mlsanity.com/paper/2504.15637/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 112 references that are in the map.
- First posted on arXiv 22 Apr 2025.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs](https://mlsanity.com/paper/2312.05934/) (2023)
- [Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPT](https://mlsanity.com/paper/2304.00385/) (2023)
- [InferFix: End-to-End Program Repair with LLMs](https://mlsanity.com/paper/2303.07263/) (2023)
- [Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair](https://mlsanity.com/paper/2309.00608/) (2023)
- [Spectre Attacks: Exploiting Speculative Execution](https://mlsanity.com/paper/1801.01203/) (2018)
- [HIPPODROME: Data Race Repair using Static Analysis Summaries](https://mlsanity.com/paper/2108.02490/) (2021)
- [A Study of Real-World Data Races in Golang](https://mlsanity.com/paper/2204.00764/) (2022)
- [Data Race Detection on Compressed Traces](https://mlsanity.com/paper/1807.08427/) (2018)
- [What Happens - After the First Race? Enhancing the Predictive Power of Happens - Before Based Dynamic Race Detection](https://mlsanity.com/paper/1808.00185/) (2018)
- [Optimistic Concurrency Control for Real-world Go Programs (Extended Version with Appendix)](https://mlsanity.com/paper/2106.01710/) (2021)
- [Dynamic Data-Race Detection through the Fine-Grained Lens](https://mlsanity.com/paper/2107.03569/) (2021)
- [Unveiling and Vanquishing Goroutine Leaks in Enterprise Microservices: A Dynamic Analysis Approach](https://mlsanity.com/paper/2312.12002/) (2023)
- [Optimistic Prediction of Synchronization-Reversal Data Races](https://mlsanity.com/paper/2401.05642/) (2024)

## Built on by (most cited first, 1 of 1)

- [BitsAI-Fix: LLM-Driven Approach for Automated Lint Error Resolution in Practice](https://mlsanity.com/paper/2508.03487/) (2025)

## Abstract (arXiv)

Data races are a prevalent class of concurrency bugs in shared-memory parallel programs, posing significant challenges to software reliability and reproducibility. While there is an extensive body of research on detecting data races and a wealth of practical detection tools across various programming languages, considerably less effort has been directed toward automatically fixing data races at an industrial scale. In large codebases, data races are continuously introduced and exhibit myriad patterns, making automated fixing particularly challenging. In this paper, we tackle the problem of automatically fixing data races at an industrial scale. We present Dr.Fix, a tool that combines large language models (LLMs) with program analysis to generate fixes for data races in real-world settings, effectively addressing a broad spectrum of racy patterns in complex code contexts. Implemented for Go--the programming language widely used in modern microservice architectures where concurrency is pervasive and data races are common--Dr.Fix seamlessly integrates into existing development workflows. We detail the design of Dr.Fix and examine how individual design choices influence the quality of the fixes produced. Over the past 18 months, Dr.Fix has been integrated into developer workflows at Uber demonstrating its practical utility. During this period, Dr.Fix produced patches for 224 (55%) from a corpus of 404 data races spanning various categories; 193 of these patches (86%) were accepted by more than a hundred developers via code reviews and integrated into the codebase.