LEMMA-RCA: A Large Multi-modal Multi-domain Dataset for Root Cause Analysis

Lecheng Zheng, Zhengzhang Chen, Dongjie Wang, Chengyuan Deng, Reon Matsuoka +1 more
6/8/2024
cs.AIcs.LG

No official code found. Best implementation: KnowledgeDiscovery/rca_baselines (34 stars, last commit 2025-10-06).

Abstract

Root cause analysis (RCA) is crucial for enhancing the reliability and performance of complex systems. However, progress in this field has been hindered by the lack of large-scale, open-source datasets tailored for RCA. To bridge this gap, we introduce LEMMA-RCA, a large dataset designed for diverse RCA tasks across multiple domains and modalities. LEMMA-RCA features various real-world fault scenarios from IT and OT operation systems, encompassing microservices, water distribution, and water treatment systems, with hundreds of system entities involved. We evaluate the quality of LEMMA-RCA by testing the performance of eight baseline methods on this dataset under various settings, including offline and online modes as well as single and multiple modalities. Our experimental results demonstrate the high quality of LEMMA-RCA. The dataset is publicly available at https://lemma-rca.github.io/.

View on arXivView PDF

Code Implementations(1)

KnowledgeDiscovery/rca_baselinesCommunity67%

Code for "LEMMA-RCA: A Large Multi-modal Multi-domain Dataset for Root Cause Analysis" paper

348Shell, PythonMay 21, 20241 years agoNOASSERTION
causal-discoverylog-analysismulti-modal-learningonline-learningroot-cause-analysis+1 more

Similar Papers

Root Cause Analysis Method Based on Large Language Models with Residual Connection Structures

83% match2026

BALANCE: Bayesian Linear Attribution for Root Cause Localization

81% match1 repo152023

PyRCA: A Library for Metric-based Root Cause Analysis

80% match1 repo5662023

Exploring LLM-based Agents for Root Cause Analysis

79% match2024

Causal AI-based Root Cause Identification: Research to Practice at Scale

79% match2025

TN-AutoRCA: Benchmark Construction and Agentic Framework for Self-Improving Alarm-Based Root Cause Analysis in Telecommunication Networks

78% match2025

Cite this paper

@article{zheng2024lemmarca,
  title  = {LEMMA-RCA: A Large Multi-modal Multi-domain Dataset for Root Cause Analysis},
  author = {Lecheng Zheng and Zhengzhang Chen and Dongjie Wang and Chengyuan Deng and Reon Matsuoka and Haifeng Chen},
  year   = {2024},
  eprint = {2406.05375},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.05375v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.05375.svg)](https://codeofpaper.com/paper/2406.05375)

Discussion