# PredicateFix: Repairing Static Analysis Alerts with Bridging Predicates

arXiv: https://arxiv.org/abs/2503.12205 · HTML: https://mlsanity.com/paper/2503.12205/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in RAG for code, one of 15 directions in Retrieval-augmented generation.
- Builds on 19 of its 67 references that are in the map.
- First posted on arXiv 15 Mar 2025.

## Placed in

- Retrieval-augmented generation / [RAG for code](https://mlsanity.com/rag/rag-for-code/)

## Builds on (most cited first, 19 of 19)

- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [AutoCodeRover: Autonomous Program Improvement](https://mlsanity.com/paper/2404.05427/) (2024)
- [Software Testing with Large Language Models: Survey, Landscape, and Vision](https://mlsanity.com/paper/2307.07221/) (2023)
- [SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair](https://mlsanity.com/paper/1901.01808/) (2018)
- [InferFix: End-to-End Program Repair with LLMs](https://mlsanity.com/paper/2303.07263/) (2023)
- [IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities](https://mlsanity.com/paper/2405.17238/) (2024)
- [Graph-based, Self-Supervised Program Repair from Diagnostic Feedback](https://mlsanity.com/paper/2005.10636/) (2020)
- [MarsCode Agent: AI-native Automated Bug Fixing](https://mlsanity.com/paper/2409.00899/) (2024)
- [Repair Is Nearly Generation: Multilingual Program Repair with LLMs](https://mlsanity.com/paper/2208.11640/) (2022)
- [A Syntax-Guided Edit Decoder for Neural Program Repair](https://mlsanity.com/paper/2106.08253/) (2021)
- [What Makes Good In-context Demonstrations for Code Intelligence Tasks with LLMs?](https://mlsanity.com/paper/2304.07575/) (2023)
- [RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair](https://mlsanity.com/paper/2309.06057/) (2023)
- [Getafix: Learning to Fix Bugs Automatically](https://mlsanity.com/paper/1902.06111/) (2019)
- [ReposVul: A Repository-Level High-Quality Vulnerability Dataset](https://mlsanity.com/paper/2401.13169/) (2024)
- [A Manually-Curated Dataset of Fixes to Vulnerabilities of Open-Source Software](https://mlsanity.com/paper/1902.02595/) (2019)
- [AVATAR : Fixing Semantic Bugs with Fix Patterns of Static Analysis Violations](https://mlsanity.com/paper/1812.07270/) (2018)
- [Mining Fix Patterns for FindBugs Violations](https://mlsanity.com/paper/1712.03201/) (2017)
- [StaticFixer: From Static Analysis to Static Repair](https://mlsanity.com/paper/2307.12465/) (2023)
- [Patch Space Exploration using Static Analysis Feedback](https://mlsanity.com/paper/2308.00294/) (2023)

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

- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing](https://mlsanity.com/paper/2506.16136/) (2025)
- [FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair](https://mlsanity.com/paper/2603.17826/) (2026)
- [Collaborative Agents for Automated Program Repair in Ruby](https://mlsanity.com/paper/2511.03925/) (2025)
- [From Benchmark Data To Applicable Program Repair: An Experience Report](https://mlsanity.com/paper/2508.16071/) (2025)

## Abstract (arXiv)

Fixing static analysis alerts in source code with Large Language Models (LLMs) is becoming increasingly popular. However, LLMs often hallucinate and perform poorly for complex and less common alerts. Retrieval-augmented generation (RAG) aims to solve this problem by providing the model with a relevant example, but existing approaches face the challenge of unsatisfactory quality of such examples. To address this challenge, we utilize the predicates in the analysis rule, which serve as a bridge between the alert and relevant code snippets within a clean code corpus, called key examples. Based on this insight, we propose an algorithm to retrieve key examples for an alert automatically, and build PredicateFix as a RAG pipeline to fix alerts from two static code analyzers: CodeQL and GoInsight. Evaluation with multiple LLMs shows that PredicateFix increases the number of correct repairs by 27.1% ~ 69.3%, significantly outperforming other baseline RAG approaches.