Research map / Probabilistic and scientific modeling / Causal discovery
Root Cause Analysis of Failures in Microservices through Causal Discovery
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| add hierarchical and localized learning (RCD) on top of Psi-PC (ablation) | Psi-PC · Synthetic DAGs, 500 nodes | execution time: 150 min -> 22 s | Helped |
| add hierarchical and localized learning (RCD) on top of Psi-PC (ablation) | Psi-PC · Synthetic DAGs | top-k recall | No clear effect |
| treat failure as intervention and use CI tests with F-node instead of pairwise COV | epsilon-Diagnosis · Synthetic DAGs, many nodes | top-k recall | Helped |
| use RCD instead of AutoMAP | AutoMAP · Synthetic DAGs | top-5 recall | Helped |
| use RCD instead of CIRCA | CIRCA · Synthetic DAGs, many nodes | recall | Helped |
| use RCD instead of Psi-PC | Psi-PC · Sock-shop CPU hog Carts | top-1 recall: 0.6 -> 0.69 | Helped |
| use RCD instead of epsilon-Diagnosis | epsilon-Diagnosis · Sock-shop CPU hog Payment | top-1 recall: 0.6 -> 0.17 | Hurt |
| use RCD instead of epsilon-Diagnosis | epsilon-Diagnosis · Sock-shop memory leak Carts | top-1 recall: 0.4 -> 0.6 | Helped |
| use RCD instead of AutoMAP | AutoMAP · Sock-shop memory leak User | top-3 recall: 0.27 -> 0.84 | Helped |
Closest papers by meaning
- Root Cause Analysis in Microservice Using Neural Granger Causal Discovery (AAAI 2024 · similarity 0.87)
- Robust Root Cause Diagnosis using In-Distribution Interventions (ICLR 2025 · similarity 0.85)
- Where Root Cause Analysis Fails: A Retrieval-Reranking Decomposition (NeurIPS 2026 · similarity 0.84)
- FastPERT: Towards Fast Microservice Application Latency Prediction via Structural Inductive Bias over PERT Networks (AAAI 2025 · similarity 0.82)
- PRIM: Meta-Learned Bayesian Root Cause Analysis (NeurIPS 2026 · similarity 0.79)
- DiagEval: Trajectory-Conditioned Diagnosis for Reliable Software Evaluation with GUI Agents (NeurIPS 2026 · similarity 0.78)
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.