All demos
Coherence Energy Labs

The whole model, not just the head

Re-run the whole model in your browser

Most "verifiable AI" re-runs a tiny last step and fingerprints the rest. Here your browser re-runs the entire image model - every convolution - in deterministic integer arithmetic, and lands on the lab's exact answer, bit-for-bit. No black box, no trusted extractor. Then check an Ed25519 credential that signs the whole model. A sibling to our three-ways proof, which trades a fingerprinted extractor for higher accuracy.

checking your browser…

the model reads
re-run every layer, then verify the signature
the whole forward pass · in your browser

Re-run every layer

Starting from the quantized image (3072 integers), your browser runs all six convolution layers, the linear projection, and the int64 coherence basin - in pure integer arithmetic, no floating point on the path. It must reproduce the lab's 64 integer features, the per-class energies, and the decision exactly. This is the part everyone else fingerprints.

signed credential

Audit the whole model

An Ed25519-signed receipt whose model_sha256 covers the CNN and the basin - so the signature pins every weight, not just the head. Anyone verifies it offline, mapped to the controls a regulator asks for.

why it matters

No trusted extractor

The honest gap in most verifiable-ML is the feature extractor: it runs in float, so it is fingerprinted, not re-run. Make every layer deterministic integer and that gap closes - the entire decision, image included, is re-runnable and signable on any machine. That is the moat: not a more accurate model, a fully re-runnable one.

Honest split: running every layer in deterministic integer costs a little accuracy. This whole-integer model is on CIFAR-10; the three-ways demo is 96.8% but re-runs only the basin head and fingerprints the float extractor. Here there is no fingerprint - the model hash covers everything.

Verification log

ready.
A VGG-style CNN whose entire forward pass (six conv layers + linear projection) runs in deterministic integer arithmetic, with an int64 coherence basin head. One image decision, re-run end-to-end in your browser - bit-for-bit with the lab's CPU, native, and GPU - and signed with Ed25519 over a model hash that covers every weight. Built by Coherence Energy Labs.