Search

Subjects

Computer Science

(6)

Events

Content Types

Working Paper

(6)

Published Date

Last 3 years

(6)

Last 12 months

(5)

Last 6 months

(3)

Last 3 months

(2)

Partners

Cambridge Open Engage

(6)

Keywords

AI safety

Authors

6 results in Keywords: AI safety

Computer Science

Working Paper

THE SENTINEL SYSTEM: A GLOBAL ARCHITECTURE FOR AI GOVERNANCE AND SAFETY

emanuele colombo

Version 1 posted 16 January 2026

257

Downloads

Computer Science

Working Paper

Cascade Amplification in Administrative AI Pipelines: When Feedback Loops Turn Additive Errors into System Failures

Florian Odi Stummer

Version 1 posted 14 April 2026

Downloads

Computer Science

Working Paper

GOVERNED AUTONOMOUS INFRASTRUCTURE (GAI) The AETHELIS Ecosystem: Formal Operational Guarantees and Verifiable Governance for Autonomous Intelligence

emanuele colombo

Version 1 posted 11 August 2026

Downloads

Computer Science

Working Paper

AXIOM-1 (A1M): A Sovereign External Governance Framework for Eliminating Sycophancy and Concessive Drift in Stochastic Language Models

Mohamed Samir

Version 1 posted 04 September 2026

Downloads

Computer Science

Working Paper

Pathological Reinforcement in Sign-Gated Dual-Trace Temporal-Difference Learning: Gamma-Invariant Necessary and Sufficient Conditions and Robust Bounds

Yuta Agawa

Version 1 posted 21 August 2025

116

Downloads

Computer Science

Working Paper

The Sentinel System: A First Operational Architecture for External, Trajectory-Aware AI Oversight

Emanuele Colombo

Version 1 posted 01 May 2026

Downloads

Search

Refine Search

6 results in AI safety in Keywords: AI safety

THE SENTINEL SYSTEM: A GLOBAL ARCHITECTURE FOR AI GOVERNANCE AND SAFETY

Cascade Amplification in Administrative AI Pipelines: When Feedback Loops Turn Additive Errors into System Failures

GOVERNED AUTONOMOUS INFRASTRUCTURE (GAI) The AETHELIS Ecosystem: Formal Operational Guarantees and Verifiable Governance for Autonomous Intelligence

AXIOM-1 (A1M): A Sovereign External Governance Framework for Eliminating Sycophancy and Concessive Drift in Stochastic Language Models

Pathological Reinforcement in Sign-Gated Dual-Trace Temporal-Difference Learning: Gamma-Invariant Necessary and Sufficient Conditions and Robust Bounds

The Sentinel System: A First Operational Architecture for External, Trajectory-Aware AI Oversight

6 results in Keywords: AI safety