ENTRO-CORE

🔴 Overview

Entropy-based control is regime-dependent

"Intelligence by Design, Stability by Physics" — Samir Baladi, April 2026

ENTRO-CORE investigates entropy-based control architectures for dynamical systems. Unlike ENTRO-AI which operates as an external monitoring layer, ENTRO-CORE embeds control within the system dynamics. Key finding: PID remains optimal in stable linear systems, while entropy-based control provides benefits near critical thresholds.

21/21

Tests Passed

Unit test suite

82.5%

Improvement

Hybrid vs uncontrolled

0.339

Hybrid Final Ψ

Near-critical conditions

5

Controllers

Uncontrolled, PID, ENTRO v1/v2, Hybrid

📊 Key Finding

Regime-dependent performance

PID

Stable Linear Regime

Optimal convergence (Ψ_final = 0.017)

ENTRO-CORE

Near-Critical Regime

Prevents collapse (Ψ_final = 1.480)

Hybrid

Multi-Regime

Robust across regimes (Ψ_final = -0.012)

📐 Control Laws

ENTRO-CORE control laws

// PID Controller u_PID(t) = Kp·e(t) + Ki·∫e dt + Kd·de/dt // Kp=0.8, Ki=0.2, Kd=0.3, e(t) = -Ψ(t) // ENTRO-CORE v1 (Original) u_ENTRO(t) = w₁·σ(Ψ_norm - θ) + w₂·tanh(Ψ̇) + w₃·tanh(Ψ̈) // w₁=0.5, w₂=0.3, w₃=0.2, θ=1.4 // Hybrid Regime-Switching u(t) = { u_PID(t) if Ψ < 1.7, u_ENTRO(t) if Ψ ≥ 1.7 }

🎛️ Hybrid Controller

Regime-Switching Architecture

# pip install entro-core from entro_core.hybrid_controller import HybridController controller = HybridController(threshold=1.7) result = controller.step(psi=1.8) # → Output u(t) = 0.423 · Mode: ENTRO-CORE

📈 Validation Results

Near-Critical Performance

Controller	Final Ψ (t=20s)	Observation
Uncontrolled	0.053	Naturally stable
PID Only	0.017	Optimal convergence
ENTRO-CORE v1	-0.239	Mild overshoot
Hybrid (threshold=1.7)	-0.012	Robust performance

📦 Installation

Quick setup

# Install from PyPI pip install entro-core # Clone repository git clone https://github.com/gitdeeper10/entro-core.git cd entro-core # Install with pip pip install -r requirements.txt pip install -e . # Verify installation python -c "from entro_core import __version__; print(__version__)"

🔧 API Reference

Python interface

HybridController

Regime-switching controller combining PID and ENTRO-CORE

from entro_core.hybrid_controller import HybridController controller = HybridController(threshold=1.7) result = controller.step(psi=1.8) print(f"u = {result.u:.3f}, mode = {result.mode}")

ENTROCOREController

Original ENTRO-CORE v1 controller

from entro_core.controller import create_controller controller = create_controller("exponential") result = controller.step(psi=48.3) print(f"u = {result.u:.3f}")

DynamicsTracker

State tracker with Ψ, dΨ/dt, d²Ψ/dt²

from entro_core.dynamics import DynamicsTracker tracker = DynamicsTracker() state = tracker.update(psi_raw=48.3, utilization=0.98) print(f"Ψ_norm = {state.psi_norm:.3f}")

🧩 Core Modules

ENTRO-CORE architecture

controller.py

ENTRO-CORE v1

Original sigmoid-tanh control law

controller_v2.py

ENTRO-CORE v2

Negative feedback version

hybrid_controller.py

Hybrid

Regime-switching controller

actuator.py

Actuation

4 mapping strategies

normalize.py

Normalization

Logistic Ψ normalization

state.py

State

Ψ, dΨ/dt, d²Ψ/dt² tracker

👤 Author

Principal investigator

🔴

Samir Baladi

Interdisciplinary AI Researcher — Theoretical Physics, Statistical Mechanics & Information Theory

Ronin Institute / Rite of Renaissance

Samir Baladi is an independent researcher affiliated with the Ronin Institute, developing the Rite of Renaissance interdisciplinary research program. ENTRO-CORE is the third project (E-LAB-03) in a ten-project research program, building directly on ENTROPIA (E-LAB-01) and ENTRO-AI (E-LAB-02).

No conflicts of interest declared. All code and data are open-source under MIT License.

📧 gitdeeper@gmail.com 🔗 ORCID: 0009-0003-8903-0029 🐙 GitHub 🦊 GitLab

📝 Citation

How to cite

@software{baladi2026entrocore, author = {Samir Baladi}, title = {ENTRO-CORE: Regime-Dependent Entropy-Augmented Control}, year = {2026}, version = {0.1.0}, publisher = {Zenodo}, doi = {10.5281/zenodo.19431029}, url = {https://doi.org/10.5281/zenodo.19431029}, note = {E-LAB-03} } @article{baladi2026entropia, title = {ENTROPIA: Statistical Dynamics of Information Dissipation}, author = {Samir Baladi}, year = {2026}, doi = {10.5281/zenodo.19416737}, note = {E-LAB-01} } @software{baladi2026entroai, author = {Samir Baladi}, title = {ENTRO-AI: Entropy-Resistant Inference Architecture}, year = {2026}, version = {2.0.0}, doi = {10.5281/zenodo.19284086}, note = {E-LAB-02} }

"Intelligence by Design, Stability by Physics"