ENTRO-PATH v1.0.0
Irreducible Path Entropy in Neural Networks
A Quantitative Information-Theoretic Framework for Entropy Propagation

Copyright (c) 2026 Samir Baladi
Ronin Institute / Rite of Renaissance

This product includes software developed by:
- NumPy (BSD license)
- SciPy (BSD license)
- scikit-learn (BSD license)
- PyTorch (BSD-style license)

For complete license information, see LICENSE file.

Project Links:
- GitHub: https://github.com/gitdeeper10/entropath
- PyPI: https://pypi.org/project/entropath
- DOI: https://doi.org/10.5281/zenodo.20222840
- OSF: https://osf.io/6v4xt

Contact: gitdeeper@gmail.com

---

Core Principles:
1. Path entropy is grounded exclusively in information-theoretic quantities
2. No semantic, cognitive, or anthropomorphic assumptions
3. Reproducible computational analysis
4. Systems-level characterisation of inference behaviour
5. Experimentally observable entropy dynamics

"The framework is restricted to formal quantitative analysis of entropy propagation in artificial neural networks. Not within scope: general theories of intelligence, cognition, or consciousness; claims regarding intentionality, agency, or phenomenology; semantic or anthropomorphic interpretation of results."

