Abstract
AI-agent evaluations usually inspect a final answer, yet error may enter through evidence, retrieval, prompting, generation or decision mapping. We introduce a stochastic semantic evidence graph (SSEG), a hierarchical stochastic DAG whose language node expands into an autoregressive token subgraph and whose observable output may be a law over complete phrases. Semantic reduction and calibration are optional. We define graph-relative local defects and downstream edge influences, derive a pathwise bound on terminal error and use its nodewise terms to diagnose governance triggers. For source provenance, the graph preserves uncertain claim--passage relations and propagates sharp Fréchet bounds rather than assuming independence across sources. Across three open-weight architectures, information-equivalent changes materially alter complete-phrase laws. A controlled experiment yields no certificate violations in 5,000 cases; crossed-RAG and live Brave-retrieval experiments separate retrieval, presentation, source and interaction effects. SSEG therefore turns workflow provenance into a quantitative account of where uncertainty entered, how it propagated and whether an output is qualified for use.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29703
