Coherence Energy Labs
Get in touch →
Coherence Energy Labs

One decision, three proofs

Prove a real image decision three ways

Our coherence model (96.8% on CIFAR-10) looks at one image and decides. That exact decision is then proven to you three independent ways, live in your browser: re-run it bit-for-bit, verify a zero-knowledge proof that hides the features, and check an Ed25519-signed audit credential. A genuinely accurate model whose decision you can also re-run, prove, and audit.

checking your browser…

the model reads
three independent proofs of the same decision
1 · re-run

Recompute it

Your browser re-runs the model's int64 basin decision from its exact integer form, bit-for-bit, the same answer as the lab's CPU, native, and GPU.

2 · zero-knowledge

Prove it privately

A 807-byte Groth16 proof that the model produced this decision - without revealing the features. snarkjs verifies it right here, no server.

3 · signed credential

Audit it

An Ed25519-signed receipt anyone verifies offline, plus the exact extractor it ran, mapped to the controls a regulator asks for.

Honest split: a deep decision is a float feature extractor (the CNN) plus the int64 basin. The basin decision is what is re-run, zero-knowledge-proven, and signed above; the extractor is bound by a cryptographic fingerprint () - the honest float-provenance half.

Verification log

ready.
A WRN-28-10 + coherence basin model (96.8% on CIFAR-10). One image decision, proven three ways: the int64 basin_fp decision re-run bit-for-bit, a circom + snarkjs Groth16 proof over the model's exact integer constants (features private), and an Ed25519-signed, re-runnable receipt. Same decision, three proofs - on a genuinely accurate model. Built by Coherence Energy Labs.