auditable decision framework 1graph fraud detection 1provenance constraints 1relational evidence fusion 1validation gating 1
From the 1 of 3 linked papers with an AI index.
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Diagnose Before You Compress: Prediction-Independent Bottleneck Witness Refinement for LLM Serving Traces
Liming Liu, Chao Hu, Mingfei Lu +7
Production LLM serving generates millions of diverse requests, making full-trace replay across serving configurations increasingly expensive. Existing trace reduction methods mainl…
cs.AI2026
PREF-Gate: Provenance-Constrained Relational Evidence Fusion with Validation-Gated Selection for Graph Fraud Detection
Liming Liu, Chao Hu, Mingfei Lu +3
The paper introduces PREF-Gate, an auditable framework that decides between using label‑free graph context or label‑derived neighborhood evidence for fraud detection on graphs, bas…