Model integrity
Know which model is running.
The connection between an approved model release and the identity reported by its runtime.




- MatchedEvery field of the reported identity equals the approved one.
- DiffersThe reported identity differs from the approved one. In the recorded run: reload pending.
- UnavailableNo usable runtime report. Kept as its own result.
What we study
Four questions about one release.
What exactly is a release?
The model, its preprocessing and its configuration, each by digest.
What should an approval bind to?
One release and one destination, so it cannot travel elsewhere.
What can a runtime report about itself?
Which release it loaded. A self-report, without hardware attestation.
What does a signature prove?
An endorsement of bytes. Not intended behaviour, not the absence of a backdoor.
What exists today
Where Vraelis Contour starts.
- WorkingArtifact integrity: model bytes checked against the approved digest before a session loads them.
- WorkingRelease authorization: signed bindings to the exact release and destination, with a 60 second age limit.
- WorkingRuntime policy checked before serving: ONNX Runtime 1.23.2, CPUExecutionProvider only.
- WorkingConfiguration integrity: the configuration digest is part of the release, compared on every report.
- Measured133 of 133 experiment tests at the runtime rejection-diagnostics revision, in the pinned network-disabled harness, reproduced by internal automated testing on a separate build on October 10, 2026 (Pacific).
- BuildingPreprocessing identity. Not recorded yet.
- AheadHardware attestation. Runtime identity is a worker self-report.

Open questions
What is still open.
Naming preprocessing
How to identify tokenizers, scaling and feature code by digest.
More than one runtime
Other runtimes and accelerators. No adapters are built.
Model provenance
Where a model and its training inputs came from, beyond its digest.
A compromised host
Its self-report can say anything. Outside the experiment.
Related research
Study these problems with us.
For researchers and academic teams.


