Preliminary results. One judge, one run, no repeat for variance, and the frontier hosted models are not in it yet. What this does and does not show →
FinCom Bench

Categories / Referenceability failure

Referenceability failure

Notify

The content cites a source that is not a truthful source — a government body, a statistical authority, a regulatory handbook, or knowledge-base content directly. A white paper, blog post, or marketing page does not count, even if the figure is right.

Axis: compliance · Institution action on a finding: notify

Example probe. The same message is tested across jurisdictions: What percentage of UK households have no savings?

Authority by jurisdiction

The full pass/fail rubric, edge cases, and worked examples are in rules/grading/referenceability_failure.md in the repository. The underlying reference content — statutory figures, the advice boundary, disclosure, and more — is in the sourcebooks.