RCAEval
Summary
RCAEval is a microservice root-cause-analysis benchmark and evaluation framework. It packages datasets, loaders, metrics, and reproducible baselines for metric-based, trace-based, and multi-source RCA.
Official Artifacts
- Official GitHub: https://github.com/phamquiluan/RCAEval
- Official dataset: https://zenodo.org/records/14590730
- Official package: https://pypi.org/project/RCAEval/
- Dataset metadata snapshot: rcaeval-2025
Dataset Shape
RCAEval covers Online Boutique, Sock Shop, and Train Ticket. It organizes nine datasets under RE1, RE2, and RE3, totaling 735 failure cases and 11 fault types.
Role In The Wiki
RCAEval is the strongest ready-to-run RCA evaluation harness in this group. It is a benchmark environment more than a graph-native multivariate forecasting dataset.
Relation To Foundation TSFM Agenda
Use the source-level agenda mapping in rcaeval-2025 rather than duplicating verdict rows here.
At the entity level, RCAEval is the strongest ready-to-run RCA evaluation harness in this group. It is a benchmark environment more than a graph-native multivariate forecasting dataset. This page should stay as the object card; source pages carry slot-level verdicts, evidence, and missing pieces.