{
  "id": 18021,
  "url": "https://arxiv.org/abs/2608.09246v1",
  "title": "An Explainable GNN Framework for Component-Level Anomaly Diagnosis",
  "summary": "Industrial processes are complex systems composed of multiple interacting sensors that generate multivariate time series (MTS). Detecting anomalies in such systems is critical for reliability and safety, yet understanding their origin is equally important. Existing Graph Neural Network (GNN)based methods for anomaly detection primarily focus on sensor-level deviations and either attribute anomalies directly to the deviating sensors. When diagnosis is attempted, generally, the most deviated senso",
  "authors": "Sena Ozgunay, Louise Travé-Massuyès, Jean-Michel Loubes, Raul Sena Ferreira",
  "category": "research",
  "topics": "healthcare,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-10T08:08:36.000Z",
  "fetched_at": "2026-08-11T05:10:37.351Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/18021",
  "original_url": "https://arxiv.org/abs/2608.09246v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}