Research map / Probabilistic and scientific modeling / Causal discovery
Root Cause Analysis of Failures in Microservices via Bayesian Root Cause Discovery
Kenneth Lee, Zihan Zhou, Murat Kocaoglu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| give the service map as the causal graph instead of a discovered CPDAG (BRCD-C) (ablation) | BRCD · Petshop (average) | top-1 accuracy: 0.40 -> 0.57 | Improved |
| give the service map as the causal graph instead of a discovered CPDAG (BRCD-C) (ablation) | BRCD · Petshop (average) | top-3 accuracy: 0.56 -> 0.68 | Improved |
| enforce service-map ancestral relations in BOSS (BRCD-M) (ablation) | BRCD · Petshop (average) | top-1 accuracy: 0.40 -> 0.48 | Improved |
| add bootstrapping with 100 observational samples (BRCD-B100) (ablation) | BRCD · Petshop (average) | top-1 accuracy: 0.40 -> 0.47 | Improved |
| add bootstrapping with 100 observational samples (BRCD-B100) (ablation) | BRCD · Petshop (average) | top-5 accuracy: 0.62 -> 0.73 | Improved |
| add bootstrapping with 10 observational samples (BRCD-B10) (ablation) | BRCD · Petshop (average) | top-1 accuracy: 0.40 -> 0.40 | No clear effect |
| add bootstrapping with 10 observational samples (BRCD-B10) (ablation) | BRCD · Petshop (average) | top-3 accuracy: 0.56 -> 0.65 | Improved |
| use BRCD instead of RCD | RCD · Petshop (average) | top-1 accuracy: 0.30 -> 0.40 | Improved |
| use BRCD instead of RCD with learned CPDAG under latent confounders | RCD · Synthetic with latent confounders | top-1 accuracy: 0.50 -> 0.60 | Improved |
| use BRCD instead of RCD for two root causes | RCD · Synthetic, two root causes | accuracy: 0.90 -> 0.90 | No clear effect |
| use BRCD instead of RCG for two root causes | RCG · Synthetic, two root causes | accuracy: 0.80 -> 0.90 | Improved |
| use BRCD instead of BARO and SimpleRCA | BARO / SimpleRCA · Online Boutique and Sockshop | top-l accuracy | Hurt |
Closest papers by meaning
- Robust Root Cause Diagnosis using In-Distribution Interventions (ICLR 2025 · similarity 0.88)
- Root Cause Analysis in Microservice Using Neural Granger Causal Discovery (AAAI 2024 · similarity 0.86)
- Where Root Cause Analysis Fails: A Retrieval-Reranking Decomposition (NeurIPS 2026 · similarity 0.84)
- PRIM: Meta-Learned Bayesian Root Cause Analysis (NeurIPS 2026 · similarity 0.83)
- Root Cause Analysis of Outliers with Missing Structural Knowledge (NeurIPS 2025 · similarity 0.81)
- FastPERT: Towards Fast Microservice Application Latency Prediction via Structural Inductive Bias over PERT Networks (AAAI 2025 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
