TAG ARCHIVE
graph-rag
2 MARIA OS blog articles tagged graph-rag. Evidence bundles, retrieval architecture, Graph RAG, knowledge trust, and auditable reasoning pipelines. This canonical topic archive supports search engines and LLM retrieval.
Agentic Company Architecture
Research on human-agent organizations, delegation boundaries, role topology, and governed autonomy.
Responsibility Gates and AI Governance
Safety, accountability, fail-closed gates, auditability, and human-in-the-loop control for AI agents.
Multi-Agent Mathematics
Formal models for convergence, stability, game theory, graph dynamics, and multi-agent evaluation.
Evidence, RAG, and Knowledge Governance
Evidence bundles, retrieval architecture, Graph RAG, knowledge trust, and auditable reasoning pipelines.
Graph RAG for Causal Structure Extraction: Matrix Methods for Multi-Hop Retrieval with Evidence Cohesion
How organizational knowledge graphs enable responsibility chain tracing and risk concentration detection
Standard RAG often retrieves flat document chunks that under-represent relational structure needed for causal and responsibility reasoning. Graph RAG models documents and entities as nodes in an adjacency matrix, enabling multi-hop retrieval along causal paths in organizational knowledge. We formalize an h-hop diffusion score, derive hop-depth choices from a noise-accuracy tradeoff, and introduce an evidence-cohesion metric that gates response generation by subgraph density. In contract-corpus evaluations, the method reported 73.4% causal-path extraction accuracy at 3 hops, a 31% improvement over flat Top-k RAG for responsibility-chain identification, and `r = 0.87` correlation between cohesion score and response correctness.
Graph RAG Matrix Modeling and Stable Hop Count Derivation
Spectral analysis of adjacency matrices reveals the optimal diffusion depth that maximizes signal-to-noise ratio in knowledge graph retrieval
Graph-based Retrieval Augmented Generation traverses knowledge graphs to gather context for language-model prompts. Each additional hop `h` in `A^h` can add useful context but also amplify noise through irrelevant paths. This paper models diffusion as matrix exponentiation with decay, derives signal-to-noise behavior by hop count using spectral decomposition, and identifies an optimal hop count `h*`. Across four enterprise knowledge graphs, the derived `h*` reduced hallucination rate by 43% versus fixed-depth traversal.