explainable ai

Understanding P.A.L.O. and PolicyWatcher

AI governance becomes difficult when the evidence behind a decision is distributed across provider policies, technical dependencies, internal controls, and changing system versions. This report explains how PALO and PolicyWatcher connect these elements in a workflow that supports accountable review. The first part intr...

Artificial intelligence-driven continuous auditing: Machine learning frameworks for real-time fraud detection in digital budgets and enterprise systems

It is stated that continuous auditing is evolving from a compliance tool to a governance component, and holes in the metrics used to evaluate, less test on real-world behaviors and yet uncorrected data privacy issues in the studies hamper the potential for repeatability and adoption.

Algorithmic Transparency and Explainable AI for Hardware Design

The increasing reliance on Artificial Intelligence (AI) in hardware design presents both significant opportunities and challenges. While AI algorithms can accelerate the design process and optimize performance, their "black box" nature raises concerns regarding trust, accountability, and potential biases. This paper ar...

Explainable AI via Causal Mediation Analysis of Neural Network Predictions

The increasing deployment of neural networks in critical applications necessitates methods for understanding their decision-making processes – a field often referred to as Explainable AI (XAI). Traditional XAI techniques frequently provide post-hoc explanations that lack a solid causal foundation, potentially masking s...

When AI Capability Outpaces Governance: Governance–Capability Misalignment in Educational Leadership

This study extends AI Governance–Capability Misalignment (AI-GCM) into educational leadership and AI-mediated institutional decision-making. It examines how governance arrangements that were initially appropriate can become misaligned when AI capabilities and their substantive influence over institutional decisions evo...

The Natural-Chance Red Line IV Formal Appendix: Canonical A+B-K-T Coupling and the Observable Red Line

Formal Appendix IV is the fourth cumulative stage of the 2026 Natural-Chance Red Line programme. It consolidates the representational-jurisdiction criterion, the quantitative residual-fibre boundary, the Stage III Enigma-2 operationalization, and the A+B-K-T conservative bridge into a single auditable framework. The ex...

The AI Incident Response Protocol: Six Stages, and the Evidence a Reconstruction Requires

An institution asked to explain an AI failure discovers, at that moment and not before, what it wrote down. The discovery is unrecoverable. Evidence is a property of the moment a decision was taken, and an institution that did not capture it then is left assembling an account from what it can still find. It reconstruct...

Algorithmic Transparency via Formal Verification of Neural Network Explainability Methods

The increasing deployment of neural networks in critical applications necessitates a deeper understanding of their decision-making processes – a field commonly addressed through explainability methods. However, current explainability techniques often rely on approximations and heuristics, lacking rigorous guarantees ab...

Agentic AI for Autonomous Additive Manufacturing: A Conceptual Framework for Self-Correcting Production Systems

Student-Led Discussion Guideline for Current Issues in English Language Education

This guideline is designed for the first online session of the course Current Issues in English Language Education. It supports a student-led discussion model in which four students are selected by the class to guide two discussion blocks. Block 1 focuses on the Course Guide and the literature review of current issues...

Neural Symbolic Reasoning Engine

This paper proposes a novel Neural Symbolic Reasoning Engine (NSRE) designed to bridge the gap between the pattern recognition capabilities of neural networks and the logical reasoning capabilities of symbolic systems. The core claim is that combining these two approaches yields a system with enhanced knowledge represe...

Explainable AI for Reinforcement Learning through Causal Reasoning

Reinforcement learning (RL) has achieved remarkable success in various domains, from game playing to robotics. However, the "black box" nature of many RL agents presents a significant challenge, particularly in applications where transparency and trust are paramount. This work proposes a novel approach to explainable A...