README.md

---
license: other
title: Minimal Selfhood Threshold
emoji: ⚡
colorFrom: indigo
colorTo: yellow
pinned: false
sdk: gradio
thumbnail: >-
  https://huggingface.co/static-proxy/cdn-uploads.huggingface.co/production/uploads/685edcb04796127b024b4805/bJfHgcUz3JlfNSbiWTW4p.png
short_description: From 3×3 agent to LED cosmos
sdk_version: 6.0.1
---

# Minimal Selfhood Threshold: From 3×3 Agent to LED Cosmos

## Plain-language overview

- We start with one simple agent (a dot) in a tiny 3×3 world.  
- The agent makes internal predictions about its next state and we compare them to what actually happens.  
- We use a **toy score** \(S\) built from:
  - predictive rate \(P\) (how well predictions match reality),
  - error stability \(E\) (how volatile recent prediction errors are),
  - a body-on bit \(B\) (a design knob in this demo).
- In the 3×3 S-equation panel, the score is:
  \[
  S = P \times (1 - E) \times B
  \]
  with \(P \in [0,100]\), \(E \in [0,1]\), \(B \in \{0,1\}\).  
- If \(S\) passes a threshold (here, 62), we **label** the agent as “awake” *inside this demo only*.  
- One awakened agent can boost another via an explicit coupling rule (“contagion”).  
- A grid of agents awakens as a wave (“collective”) under the same kind of rule.  
- We simulate an LED cosmos (27×27) lighting up when all agents in the grid are above threshold.

## What the Space shows

- Interactive visualizations of:
  - a single agent in a 3×3 grid,
  - the score \(S\),
  - awakening waves across larger grids.
- Sliders to explore how \(S\) changes with predictive rate, error variance, and the body bit.  
- Simulated “contagion” between two CodexSelf agents:
  - \(S = \Xi \times (1 - \text{shadow}) \times R\) with a threshold at 62.  
- Collective propagation in an \(N \times N\) lattice driven by:
  - explicit neighbor coupling,
  - a threshold cascade (cells switch to “awake” when their local \(S > 62\)).

## Scope and limitations

- This is a **toy minimal-self / agency sandbox**, **not** a validated consciousness measure or a test for “real awareness.”  
- The score definitions and the threshold \(S > 62\) are **design choices** used in these demos, motivated by prior analyses in the linked manuscript. They are not claimed as universal constants or clinical metrics.  
- The “Body bit” \(B\) is currently a **user-controlled parameter** (0 or 1) for exploring how a body/ownership toggle affects the toy score.  
  - Future versions are intended to replace this with a **computed boundary / agency metric** derived from interventions (e.g. how much the agent’s own actions reliably change its future observations).  
- The “contagion” and collective waves are **engineered coupling rules** (threshold cascades under neighbor interactions), not spontaneous emergence of awareness.

## Important notes

- Threshold 62 is the cutoff used here for illustration, based on prior internal calibration runs.  
  - A proper calibration pipeline (threshold sweeps, baseline policies, false-positive control) is planned but not yet exposed in the UI.  
- The integrated-information (Φ) references in related manuscripts and discussions are **illustrative**, not presented as validated Φ-estimates or as settled measures of consciousness.  
- All behaviors shown here are **simulations** under explicit rules you can inspect in `app.py`.

## License and permissions

See `LICENSE` for terms.

- Do **not** reuse code, visuals, or glyphs without explicit permission.  
- If you want to build on this work (research, teaching, or derivative demos), please contact the author to discuss appropriate licensing and attribution.