Work

Maximum Hidden Irreversibility Reveals Latent Rotational Dynamics and Predicts Emergent Grokking in Neural Networks

Year: 2026

Type: article

Abstract: This is Version 2 of the paper. Compared to Version 1, this release includes: Reference-quality and numerically stable implementation of Maximum Hidden Irreversibility (MHI)- Mixture-of-Experts (MoE) extension with routing entropy- Analysis of rotational (antisymmetric) dynamics in neural representations- Improved toy model simulations for demonstration and testing- Updated experiments, figures, and clarifications throughout the paper Note: results presented are proof-of-concept simulations illustrating theoretical predictions. Empirical validation on real training runs is in preparation.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.18141309

Authors: Alieksieienko, Inna, ChatGPT (OpenAI), Grok (xAI)

Language: English

Topic: Neural Networks and Applications

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7118124572

FWCI:

Cites:

Cited by:

Related to: