Beyond Prediction -- Structuring Epistemic Integrity in Artificial Reasoning Systems
This addresses the need for more reliable and auditable AI reasoning systems, particularly for applications requiring strict epistemic integrity, though it appears incremental as it builds on existing symbolic and knowledge-based methods.
The paper tackles the problem of AI systems lacking structured reasoning and truth-preserving capabilities by developing a comprehensive framework that integrates belief representation, metacognitive processes, and normative verification, resulting in a system supporting propositional commitment and contradiction detection.
This paper develops a comprehensive framework for artificial intelligence systems that operate under strict epistemic constraints, moving beyond stochastic language prediction to support structured reasoning, propositional commitment, and contradiction detection. It formalises belief representation, metacognitive processes, and normative verification, integrating symbolic inference, knowledge graphs, and blockchain-based justification to ensure truth-preserving, auditably rational epistemic agents.