TORAI finds fine-grained root causes in microservice failures with blind spots by measuring anomaly severity from multi-source telemetry, clustering services by symptoms, ranking via causal analysis within clusters, and aggregating with hypothesis testing.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Targeted, evidence-rich context partitions improve causal clarity and actionability of LLM failure explanations while large undifferentiated contexts produce vaguer outputs, with higher-quality explanations correlating to better downstream repair rates.
An LLM-guided safety agent on dual-modular redundant edge hardware demonstrates a practical path to ISO 13849 Category 3 and PL d compliance for human-robot interaction using cost-effective platforms.
citing papers explorer
-
TORAI: Multi-source Root Cause Analysis for Blind Spots in Microservice Service Call Graph
TORAI finds fine-grained root causes in microservice failures with blind spots by measuring anomaly severity from multi-source telemetry, clustering services by symptoms, ranking via causal analysis within clusters, and aggregating with hypothesis testing.
-
From Program Slices to Causal Clarity: Evaluating Faithful, Actionable LLM-Generated Failure Explanations via Context Partitioning and LLM-as-a-Judge
Targeted, evidence-rich context partitions improve causal clarity and actionability of LLM failure explanations while large undifferentiated contexts produce vaguer outputs, with higher-quality explanations correlating to better downstream repair rates.
-
LLM-Guided Safety Agent for Edge Robotics with an ISO-Compliant Perception-Compute-Control Architecture
An LLM-guided safety agent on dual-modular redundant edge hardware demonstrates a practical path to ISO 13849 Category 3 and PL d compliance for human-robot interaction using cost-effective platforms.