DepthMuun/gfn-gssm-xor-parity

🌀 G-SSM XOR Parity Solver (Official Checkpoint)

This repository contains the weights and configuration for the Geodesic State Space Model (G-SSM) specialized for XOR logic.

🚀 Highlights

• Architecture: Geodesic State Space Model (G-SSM).
• Parameters: 3,164 (PyTorch verified).
• Memory Scaling: Constant $O(1)$ VRAM regardless of sequence length.
• Time Scaling: Linear $O(L)$ total, constant $O(1)$ per-token step.
• Zero-Shot Logic: Infinite generalization to long bitstreams (1M+ bits).

💻 Technical Usage (Inference)

To run inference locally, you need the GFN Framework installed.

1. Install GFN Framework

pip install gfn

2. Clone this repository

git lfs install
git clone https://huggingface.co/DepthMuun/gfn-gssm-xor-parity
cd gfn-gssm-xor-parity

3. Run Inference Script

Use the included inference.py script for an interactive test:

python inference.py

Python API Example

As shown in the audited inference.py, the official way to load G-SSM models is:

import torch
from gfn import gssm

# Load model (automatically handles config.json in the same dir)
model = gssm.load("xor_best_model.bin", device="cpu")
model.eval()

# Inference
bits = torch.randint(0, 2, (1, 1000000))
with torch.no_grad():
    logits, state, info = model(bits)
    # Geometrical decoding logic is detailed in inference.py

📜 Citation

If you use this work, please cite:

@article{sturtz2026geometry,
  title={Geometric Flow Networks: A Physics-Informed Paradigm for Sequential Intelligence},
  author={Stürtz, Joaquín},
  journal={Zenodo Preprints},
  year={2026},
  doi={10.5281/zenodo.19141133},
  url={https://doi.org/10.5281/zenodo.19141133}
}

🔗 Resources

• Interactive Demo: Hugging Face Space
• Framework Source: GitHub: DepthMuun/gfn
• Official Paper: Zenodo