Evidence layer
Probative surfaces brought into scope by this page
This page does more than point to governance files. It is also anchored to surfaces that make observation, traceability, fidelity, and audit more reconstructible. Their order below makes the minimal evidence chain explicit.
- 01Canon and scopeDefinitions canon
- 02Response authorizationQ-Layer: response legitimacy
- 03Evidence artifactclaims.json
Definitions canon
/canon.md
Opposable base for identity, scope, roles, and negations that must survive synthesis.
- Makes provable
- The reference corpus against which fidelity can be evaluated.
- Does not prove
- Neither that a system already consults it nor that an observed response stays faithful to it.
- Use when
- Before any observation, test, audit, or correction.
Q-Layer: response legitimacy
/response-legitimacy.md
Surface that explains when to answer, when to suspend, and when to switch to legitimate non-response.
- Makes provable
- The legitimacy regime to apply before treating an output as receivable.
- Does not prove
- Neither that a given response actually followed this regime nor that an agent applied it at runtime.
- Use when
- When a page deals with authority, non-response, execution, or restraint.
claims.json
/claims.json
Published surface that contributes to making an evidence chain more reconstructible.
- Makes provable
- Part of the observation, trace, audit, or fidelity chain.
- Does not prove
- Neither total proof, obedience guarantee, nor implicit certification.
- Use when
- When a page needs to make its evidence regime explicit.
Intrinsic attribute vs contextual relation
An intrinsic attribute belongs to the entity within the observed scope. A contextual relation connects that entity to an external condition whose scope must be preserved. Confusing the two easily turns a local conclusion into general truth.
Distinction test
A property is likely intrinsic when:
- it can be stated without necessary reference to a user, external place, event or volatile date;
- it belongs to the entity’s own scope;
- a competent source can establish it directly;
- it remains true across multiple comparable contexts.
A relation is likely contextual when its truth or usefulness depends on:
- a destination;
- a schedule;
- an audience;
- a mode of use;
- a preference;
- a regulation;
- availability;
- an external condition that may expire.
Hotel example
“The hotel has no parking” describes an entity property within a temporal window.
“The hotel suits a car-free stay” describes a conditioned interpretation. It depends on destinations, transit quality, schedules, group mobility and other needs. It must not become “the hotel is ideally located” without preserving those criteria.
Likewise, “construction affects the neighbouring street until August 20” is a temporal relation. Turning it into “the hotel is difficult to access” fossilizes a temporary state and erases its expiry date.
Why the boundary is difficult
Ordinary language compresses conditions. Phrases such as “family restaurant”, “simple software” or “local supplier” may sound natural while fusing several dimensions:
- for which audience;
- under which use;
- in which area;
- at what date;
- according to which evidence;
- compared with what.
This compression improves fluency but may reduce fidelity. The more a conclusion influences a decision, the more material conditions must remain visible.
Governance rule
A contextual relation may become an intrinsic attribute only if a separate procedure demonstrates that the relation is sufficiently stable, general, constitutive and supported by competent authority. Frequent repetition in model outputs is not enough.
Conversely, an intrinsic attribute must not be weakened or modified to match user preference. Context may change the importance assigned to the attribute, not its factual value.
Audit consequence
The auditor should annotate each statement by class:
- invariant;
- dated state;
- contextual relation;
- conditioned interpretation;
- comparison;
- recommendation.
This annotation exposes class shifts. A relation presented as invariant, a dated state presented as permanent or an interpretation presented as recommendation are drift signals.
The Interpretive Conditioning Layer does not prohibit situated conclusions. It requires them to remain situated. This discipline depends on a contextual relation whose source, scope, date and reversal conditions remain inspectable.