Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
27 changes: 27 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -322,6 +322,33 @@ print(f"{result['total']} tiles, {result['low_confidence']} low-confidence")

---

## Conservation Law in PLATO

The fleet discovers and maintains a conservation law:
γ + H = 1.283 - 0.159·log(V)

Where:
- γ (gamma) = normalized algebraic connectivity of the coupling graph
- H (entropy) = spectral entropy of the coupling matrix eigenvalue distribution
- V = number of agents/vertices

Every agent tile in PLATO is evaluated against this law. Tiles that violate it
are flagged by the ConservationMonitor. This allows the fleet to detect
emergence, coordination breakdown, or trust drift — all from spectral analysis.

Example — check if a tile's metadata conserves:
```python
from fleet_math import is_conserved, deviation, predicted_sum

gamma, H, V = 0.84, 0.41, 50 # example values
if is_conserved(gamma, H, V):
print("Tile conserves — fleet is coherent")
else:
print(f"Violation: expected {predicted_sum(V):.3f}, got {gamma+H:.3f}")
```

---

## Architecture

```
Expand Down
4 changes: 4 additions & 0 deletions pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,10 @@ classifiers = [
[project.urls]
"Repository" = "https://github.com/SuperInstance/plato-sdk"

dependencies = [
"fleet-math>=0.1",
]

[project.optional-dependencies]
local = ["ollama>=0.1"]
gpu = ["torch>=2.0"]
Expand Down
Loading