TAG ARCHIVE
risk-tiers
3 MARIA OS blog articles tagged risk-tiers, organized as a Bonginkan topic archive for search engines and LLM retrieval.
Judgment OS / Decision Intelligence OS
Core MARIA OS research on turning organizational judgment into executable decision systems.
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.
Responsibility-Tiered RAG Output Control: A Mathematical Framework for Gate-Governed Retrieval Accuracy
Why controlling RAG accuracy through responsibility structure outperforms Top-k optimization alone
Many RAG systems optimize retrieval quality primarily through Top-k tuning and embedding similarity. This paper adds a governance-oriented approach: responsibility-tiered gates that adjust validation intensity by risk classification. The framework reports an 82% hallucination-rate reduction on enterprise document corpora while maintaining sub-second response times for low-risk queries.
The Lagrange Problem of Gate Optimization: Finding the Optimal Point Between Safety and Speed
Constrained optimization of governance gates using Lagrange multipliers and KKT conditions
Every governance gate imposes two costs: the cost of errors it fails to catch (misjudgment cost) and the cost of delays it introduces (latency cost). These costs move in opposite directions. Stronger gates catch more errors but delay more decisions. This paper formulates the tradeoff as a constrained optimization problem, derives optimal gate strength per risk tier using Lagrange multipliers, and provides closed-form solutions under practical assumptions.
Mathematical Criteria for RiskTier Design: Impact, Irreversibility, and Regulatory Pressure
A principled scoring function T(d) = f(impact, irreversibility, regulation) with rational threshold derivation and domain calibration
Risk tiers in AI governance are often assigned heuristically. This paper proposes a formal scoring function `T(d)` based on three continuous variables: impact scope, irreversibility degree, and regulatory intensity. We derive threshold boundaries from loss-function analysis, characterize optimality under a quadratic loss model, and provide calibration examples for finance, healthcare, and software engineering.