TAG ARCHIVE
responsibility-gates
6 MARIA OS blog articles tagged responsibility-gates. Safety, accountability, fail-closed gates, auditability, and human-in-the-loop control for AI agents. This canonical topic archive supports search engines and LLM retrieval.
Judgment OS / Decision Intelligence OS
Core MARIA OS research on turning organizational judgment into executable decision systems.
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.
Agentic R&D and Judgment Science
Research operations, simulation labs, judgment science, recursive improvement, and experimental AI governance.
Learning State Vector Model: Multi-Dimensional Student Modeling for Governed Educational AI
Managing student state as high-dimensional vectors with responsibility-gated interventions that prevent harmful over-optimization of learning pathways
Many educational AI systems still optimize around narrow metrics such as test scores, completion rates, or engagement time. Learning, however, is multi-dimensional: knowledge, confidence, motivation, metacognition, and social skills evolve on different trajectories. This paper introduces the Learning State Vector Model, representing each student as a high-dimensional state vector so tutoring agents can make governed decisions across dimensions and reduce harmful single-metric over-optimization.
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.
Fail-Closed Gate Design for Agent Governance: Responsibility Decomposition and Optimal Human Escalation
Responsibility decomposition-point control for enterprise AI agents
When an AI agent modifies production code, calls external APIs, or alters contracts, responsibility boundaries must remain explicit. This paper formalizes fail-closed gates as a core architectural primitive for responsibility decomposition in multi-agent systems. We derive gate configurations via constrained optimization and use internal simulations to illustrate how a 30/70 human-agent ratio can preserve responsibility coverage while reducing decision latency versus full human review.
Multi-Universe Investment Decision Engine: Conflict-Aware Capital Allocation with Fail-Closed Portfolio Optimization
Why investment decisions require conflict management across multiple evaluation universes, not single-score optimization
Traditional investment analysis often compresses multidimensional evaluation into a single score (for example NPV or IRR), which can hide cross-domain conflicts. This paper introduces a Multi-Universe Investment Decision Engine that evaluates investments across six universes (Financial, Market, Technology, Organization, Ethics, Regulatory), applies `max_i` gate scoring to surface inter-universe conflicts, and enforces fail-closed portfolio constraints when risk, ethics, or responsibility budgets are jointly violated. The quantitative examples in this post are synthetic scenario outputs intended to stress-test the framework rather than to advertise investable performance.
AML Detection Gate Optimization: Constrained Loss Minimization for Anti-Money Laundering
Formalizing gate strength as a continuous control variable to minimize the combined cost of false positives, missed detections, and investigation delay in AML compliance pipelines
AML programs face a costly tradeoff between false positives, missed detections, and investigation delay. This paper formalizes AML detection as constrained loss minimization over gate strength `g` and treats the benchmark numbers as synthetic scenario outputs, not as universal regulatory thresholds or turnkey compliance claims. The practical value of the article is in the control framework, escalation logic, and risk-based calibration structure.
Game Theory of Agent Organizations: Designing for Stable Cooperation in Repeated Play
Sanctions and visibility can sustain cooperation without claiming universal Nash miracles
Multi-agent organizations drift toward local selfishness when the immediate gain from defecting is larger than the immediate gain from cooperating. This article models that pressure using repeated games, then shows how evidence visibility, sanctions, and future access costs can make cooperation the safer long-run strategy. The result is a practical calibration rule rather than an overstated proof of a unique equilibrium in production settings.