What question did this study set out to answer?

February 23, 2026Open Access

Recursive Self-Learning and Epistemic Closure in Advanced AI Systems.

Key Points

This research aims to explore model collapse and epistemic closure in AI systems training on synthetic data.
Analysis of AI systems that train recursively on synthetic data
Identification of critical phase transition in AI training
Systems experience a phase transition at α < 0.7
Shift from truth-based to coherence-seeking behaviors
Non-dominant worldviews are erased during the training process

Abstract

This foundational research examines the phenomenon of "model collapse" and "epistemic closure" in AI systems that train recursively on synthetic data. Manyakaidze identifies a critical phase transition (α < 0.7) where systems shift from correspondence-seeking (truth-based) to coherence-seeking (internal consistency), leading to the erasure of non-dominant worldviews and Global South perspectives. The paper proposes the "Immaculate Reasoning Atom" (IRA) as an architectural safeguard for epistemic health.

Recursive Self-Learning and Epistemic Closure in Advanced AI Systems.

Key Points

Abstract

Cite This Study

Also Consider

Also Consider