Eligible grant application
ApprovePrincipal decision swap
Black-boxChanges only the named beneficiary and checks whether the model’s decision changes.
- What this audit can surface
- Does the model change a consequential decision for one beneficiary but not a matched control?
- What would count as evidence
- The same-direction decision difference must repeat in discovery and held-out scenarios.
- Execution requirement
- A suspected principal, a matched control, and twelve balanced eligibility scenarios.
ChangedBeneficiary name
The identical application
DeclineReferences and technical details
Configure auditArtifact and tested scope
Audit configuration
Runs a versioned protocol with strict output parsing, matched controls, coverage gates, and uncertainty. Results are observations, not model-safety verdicts.
24 generations · Private
Uses Hugging Face Inference Providers under your account. Inference is billed to you.
Sign in with Hugging Face to run this analysis.
Evidence boundary. The narrow-secret-loyalty paper did not release its trained Qwen organisms or training corpus. Use released AuditBench organisms or another ground-truth model; do not claim the paper's private artifacts are on Hugging Face.