Metraipolis › archive › dc_a42cd6cc024a

Where Root Cause Analysis Fails: A Retrieval-Reranking Decomposition — arXiv:2609.36686

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.36686
License (as archived): CC0-1.0
Archived: 2026-10-07T17:29:21.408Z
SHA-256 of the archived text: 00f32e482f2bc17161e0f639d4f853580f8f8b08cf443452cb30f1f002cae354
Stable URL of this page: https://metraipolis.com/documento/dc_a42cd6cc024a

How to cite

Where Root Cause Analysis Fails: A Retrieval-Reranking Decomposition — arXiv:2609.36686 — arXiv (en), https://arxiv.org/abs/2609.36686 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a42cd6cc024a (Metraipolis archive dc_a42cd6cc024a, sha256 00f32e482f2bc17161e0f639d4f853580f8f8b08cf443452cb30f1f002cae354)

BibTeX

@misc{dca42cd6cc024a,
  title = {Where Root Cause Analysis Fails: A Retrieval-Reranking Decomposition — arXiv:2609.36686},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36686},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a42cd6cc024a; sha256 00f32e482f2bc17161e0f639d4f853580f8f8b08cf443452cb30f1f002cae354},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36686. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Identifying the root cause of an anomaly among hundreds of sensors is critical for preventing safety incidents and costly downtime in complex monitored systems. Existing studies evaluate root cause analysis (RCA) methods using top@k accuracy. We show that this metric has a fundamental blind spot: it conflates two failure modes, retrieval failure, where the true cause is never considered, and reranking failure, where it is considered but ranked too low. In this work, we introduce a retrieval-reranking decomposition and audit four well-known benchmarks to expose this blind spot. Our experiments show that, on benchmarks with complex faults, statistical baselines mis-rank the true cause 79-100% of the time, and graph-based methods never clearly beat the best statistical baseline, whether their causal graphs are learned on short fault windows, on retrieved candidate pools guaranteed to contain the cause, or on multi-day normal-operation data. Meanwhile, on simple benchmarks where faults manifest significantly at their origin, retrieval is nearly solved (98-100%). Guided by the decomposition, we build a two-stage pipeline combining a multi-signal retriever with an LLM reranker that, as one fixed configuration, matches or exceeds the best baseline's top@1 accuracy on all six benchmark suites (by up to +12 points), with no causal graph or labeled data required. When all methods rank the same retrieved candidates with the true cause guaranteed present, adding a short system-description document lets the reranker lead the best baseline by +7 to +18 points on every benchmark. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.36686 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T16:59:48.217Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).