PRAXIS combines LLM-driven structured traversal of service dependency graphs and hammock-block program dependence graphs to improve root-cause analysis accuracy by up to 6.3x while cutting token consumption by 5.3x on 30 real-world cloud incidents.
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining , pages =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
A latent-cluster quasi-Bayesian method with restarted updates yields sublinear cumulative Wasserstein-1 regret for online distributional prediction under drift and adversarial corruption.
TingIS uses multi-stage LLM event linking plus routing and filtering to extract high-priority incidents from noisy customer data at 2,000 messages per minute, delivering 3.5-minute P90 latency and 95% discovery in production.
citing papers explorer
-
Online Distributional Prediction via Latent Cluster Geometry Under Drift and Corruption
A latent-cluster quasi-Bayesian method with restarted updates yields sublinear cumulative Wasserstein-1 regret for online distributional prediction under drift and adversarial corruption.