A single-file Python CLI that pre-registers AI/ML accuracy claims with SHA-256. Lock the threshold before the data, or it didn't happen.
-
Updated
May 16, 2026 - HTML
A single-file Python CLI that pre-registers AI/ML accuracy claims with SHA-256. Lock the threshold before the data, or it didn't happen.
Public scorecard of how 25+ ML eval claims meet 9 PRML falsifiability criteria. CC0 data; MIT tooling.
PRML pre-registration adapter for Inspect AI eval logs. MIT.
Field manual for the PRML v0.1 specification. 8 patterns, 4 anti-patterns, 4 working examples. CC0.
Verify PRML (Pre-Registered ML Manifest) commitments in CI. Block merges on tampered or regressed eval claims.
JavaScript reference implementation of the PRML (Pre-Registered ML Manifest) v0.1 specification. Byte-equivalent to the Python reference across 20 conformance vectors. Zero runtime dependencies.
Add a description, image, and links to the threshold-pre-registration topic page so that developers can more easily learn about it.
To associate your repository with the threshold-pre-registration topic, visit your repo's landing page and select "manage topics."