Risk framing
This note addresses systemic interpretive risk — the kind that accumulates without spectacular failure, compounding into structural damage. The specific concern: canonical silence: when the correct output is a non‑answer.
Sometimes the best output is “I don’t know”. Canonical silence protects users when evidence is missing or out of scope. Refusal becomes a governed capability.
The doctrinal stake is precise: Normalize non-answers when evidence is missing or out of scope.
Systemic mechanism
The mechanism operates on several levels. Turn “I don't know” into a governed output rather than a UX failure. This is not a marginal edge case — it reflects how generative systems handle ambiguity, competing sources, and incomplete information when explicit governance constraints are absent.
A further dimension compounds the problem: Avoid invented answers that create interpretive debt. When multiple factors interact without governance, the system produces outputs that are internally consistent yet may diverge from canonical meaning. The result is not a single detectable error but a pattern of drift.
The practical consequence is measurable: ungoverned interpretation accumulates as interpretive debt — small deviations that individually appear trivial but collectively reshape perceived reality. The cost of correction scales with propagation depth, making early governance intervention significantly more efficient than retroactive repair.
Governance response
Making this risk detectable before it becomes structural requires observable signals published in machine-readable form. Both human auditors and automated agents need markers that distinguish confident error from genuine authority. Without detection, correction becomes retroactive and expensive.
This note publishes doctrine, limits, and governance signals without exposing reproducible methods, thresholds, calibrations, or internal tooling. Operationalization remains available under private engagement.