ananke
verification gate
Deterministic verification gate for scientific models

Wrong models run anyway.
Catch the error before you simulate.

Paste an ODE system, PDE, reaction network, or tensor equation. ANANKE refuses the unsound ones — with the exact reason — before you waste a simulation. No LLM in the verdict.

deterministic · auditableno guessing — a witnessed refusal10 domains, one engine
a model → a verdictillustrative
dC/dt = -CL*C
C: mg/L   CL: L/hr
REFUSED · dimensional
CL is volume/time, used as a rate — the units don't balance. witness: CL
⊢ conservation⊢ positivity◇ boundedness · declare
Why a gate, not a chatbot

Ask an LLM if a model is sound — it guesses.

an LLM

Returns a confident, plausible answer. It can't tell you the dimensions don't balance, that a rate constant carries the wrong units, or that the reaction creates mass — it pattern-matches and hopes. Run it and you waste days on a model that was broken from line one.

ANANKE

Refuses with the exact reason — which variable, which law, a witness — or verifies and seals a certificate. Deterministic: the same input always gives the same verdict, and an auditor re-derives the seal from the payload alone. When it can't decide, it says so; it never guesses.

A closed basis of checks

One engine, structural truths decided without running anything.

These hold the moment you write the model — before any solver, independent of initial values. You write the model in one editor; the engine routes by what you wrote and runs the checks that apply.

dimensional consistencyconservation / mass balancepositivityboundedness / stabilitystoichiometric consistencythermodynamic loop lawPDE well-posednessmaximum principletensor index consistencystructural identifiabilitygraph / combinatorial existencetopological invariantsoptimality / equilibriumdata-processing inequality
acceptsODE systemsPDEsreaction networkstensor equationsoptimizationstate-space control
Where it fits

Not another simulator.
The step before one.

MATLAB, NONMEM, SciPy, Julia will happily integrate a broken model and draw you a confident graph. ANANKE is the gate before that: verify the model is structurally sound, get an auditable certificate, then simulate in the tool you already use. Like a type checker for scientific models.

Verify before you
trust the graph.

Paste a model. Get a verdict, a reason, and a certificate.