Skip to main content

Architecture overview

omnibias is a uv workspace monorepo built around one principle: the math has a single source of truth, and everything else specializes it.

The dependency graph

Package tiers

TierPackagesStatus
Stable workspacecore, torch, jax, ferminetstable
Keras unified backendkerasalpha
Beta extensionspinn, fields, geometrybeta
Alpha extensionsqpinn, curvature, symbolic, score, fractional, binary, boolean, spiking, hopfield, verify, dynamicsalpha

The Stability matrix is the source of truth for support guarantees.

The three registers

omnibias runs one derivative tower in three registers:

  • Differentiable — the fast, autodiff-friendly path used in training.
  • Rigorous — outward-rounded interval / affine / Taylor-model arithmetic that produces provable enclosures.
  • Formal — a Mathlib-free Lean 4 kernel that re-checks finite, rational obligations.

The verified substrate and the formal bridge are pure-Python / Lean-core and never import a backend.

Design rules

These are the invariants that keep the architecture honest:

  • The core is pure Python — it never imports torch, jax, tensorflow, or keras.
  • Polynomial coefficients are not forked per backend. Every backend imports them from omnibias.core.polynomials.
  • Backends select the closed-form path via a class marker (_omnibias_dispatch) rather than importing concrete field classes — which is why the foundational packages never import a downstream package.
  • New field-level ops are torch + jax; Keras users still get bit-identical activation-level math through OperatorBlock.

Where to look

You want…Read
The activation mathCore
How a backend specializes itBackends
The field & operator substrateField substrate
Rigorous enclosuresCertified register
The Lean gateThe formal loop