Canon-output gap
The canon-output gap is the distance between what the canon declares — truths, boundaries, negations, conditions — and what an AI system reconstructs in its answers. It measures interpretive distortion: an output can sound plausible while remaining incompatible with the canon.
This gap is a core diagnostic unit. It shifts the discussion away from opinion (“true / false”) toward a governable measurement (“compatible / incompatible with the canon”).
Definition
The canon-output gap covers the divergences between the canon — declared statements, conditions of validity, limits, governed negations — and the output — assertions, omissions, reformulations, inferences, and framings produced by the model. The gap can be produced by omission, extrapolation, substitution, recasting, contamination, or capture.
Why this matters in AI systems
- A response can sound “good” while remaining incompatible with the canon: plausibility is not fidelity.
- Smoothing hides the gap by removing conditions, limits, or exceptions without visible noise.
- Correction requires measurement; without a gap indicator, remediation remains empirical.
Types of canon-output gap
- Gap by omission: a condition exists in the canon but disappears in the output.
- Gap by extrapolation: the output exceeds the declared scope and crosses an authority boundary.
- Gap by substitution: the system silently replaces the canon with a secondary source.
- Gap by reframing: the output explains the concept in a dominant vocabulary incompatible with canonical distinctions.
Practical signals
- Conditions, limits, and exceptions never appear in the answer.
- Capabilities, rights, or promises are attributed without being declared.
- The answer varies strongly under rephrasing, which suggests unstable activation.
- The canon is cited, but the conclusion exceeds what the citation authorizes.
What it is not
- It is not a mere stylistic difference.
- It is not necessarily an attack; the gap can be structural and unintentional.
- It is not only a retrieval issue; synthesis and inference can create the gap as well.
Minimum rule
ECS-1: any high-impact answer must minimize the canon-output gap by preserving canonical boundaries, conditions, and governed negations, and by producing a proof of fidelity. If the gap cannot be reduced under the declared conditions, the correct outcome is a legitimate non-response.
Minimal governance implication
The canon-to-output gap is never just a stylistic variation. It is the measurable sign that the system has moved away from the declared source of truth. That is why gap measurement belongs to auditability, not merely to editorial comparison.
Typical forms of gap
A canon-to-output gap may take the form of omission, excessive compression, unsupported addition, shifted emphasis, or outright contradiction. The variety matters because different gaps call for different corrective responses.