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
- 02Weak observationQ-Ledger
- 03Derived measurementQ-Metrics
- 04Audit reportIIP report schema
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-Ledger
/.well-known/q-ledger.json
Public ledger of inferred sessions that makes some observed consultations and sequences visible.
- Makes provable
- That a behavior was observed as weak, dated, contextualized trace evidence.
- Does not prove
- Neither actor identity, system obedience, nor strong proof of activation.
- Use when
- When it is necessary to distinguish descriptive observation from strong attestation.
Q-Metrics
/.well-known/q-metrics.json
Derived layer that makes some variations more comparable from one snapshot to another.
- Makes provable
- That an observed signal can be compared, versioned, and challenged as a descriptive indicator.
- Does not prove
- Neither the truth of a representation, the fidelity of an output, nor real steering on its own.
- Use when
- To compare windows, prioritize an audit, and document a before/after.
IIP report schema
/iip-report.schema.json
Public interface for an interpretation integrity report: scope, metrics, and drift taxonomy.
- Makes provable
- The minimal shape of a reconstructible and comparable audit report.
- Does not prove
- Neither private weights, internal heuristics, nor the success of a concrete audit.
- Use when
- When a page discusses audit, probative deliverables, or opposable reports.
Complementary probative surfaces (1)
These artifacts extend the main chain. They help qualify an audit, an evidence level, a citation, or a version trajectory.
Citations
/citations.md
Minimal external reference surface used to contextualize some concepts without delegating canonical authority to them.
Being cited vs being understood
This page clarifies a distinction that must remain explicit on this site: a source may be cited without the object, perimeter, modality, and limits it publishes actually being understood.
The two states may coexist. They do not designate the same threshold.
Why the confusion appears
As soon as an answer shows a link, a reference, a domain name, or an official source, the temptation is strong to conclude that the understanding problem has been solved.
That shortcut feels reassuring. It remains wrong too often.
A citation shows that a source became mobilizable, consultable, or salient enough to appear in an answer. It does not yet show that the source governed the final framing, nor that its limits were preserved.
What “being cited” correctly names
Being cited correctly names a form of documentary presence.
It may designate:
- a source explicitly mentioned in the answer;
- a reference used as apparent support;
- a link or domain made visible to the user;
- a stronger signal of presence than silent background mobilization.
That is a useful threshold. It is not yet a threshold of faithful understanding.
What “being understood” adds
Being understood adds stricter constraints.
For a source, brand, or entity to count as correctly understood, the reconstruction must at minimum preserve:
- the object: what the source is actually about;
- the perimeter: what the source covers, and what it does not authorize one to extend;
- the modality: description, rule, hypothesis, exception, non-response;
- the limits: conditions, exclusions, negations, boundaries;
- the authority boundary: what still belongs to the source and what already belongs to outside inference.
At that level, citation no longer suffices. One must be able to speak of proof of fidelity, the canon-output gap, or the authority boundary.
Four cases that must stay separate
1. Cited, but poorly understood
The source is present, but the answer extends the offer, simplifies a condition, turns a description into a prescription, or removes a critical limit.
2. Cited, but framed by a third party
The official source appears, but a directory, comparator, profile, or media source imposes the dominant category, comparison, or definition.
3. Understood without explicit citation
A source may weigh strongly on the answer without being displayed in the final wording. That is precisely the issue named by structural visibility.
4. Stably cited, unstably understood
The same source returns from one answer to the next, but its perimeter, exclusions, or qualification shift depending on system, language, or prompt.
Practical reading rule used on this site
The site applies a simple rule:
- use citation for the explicit presence of a source;
- use understanding only when object, perimeter, and limits remain preserved;
- use proof of fidelity when that preservation can be shown;
- use representation gap when the diagnosis remains public and broader;
- use AI citation analysis when the investigation starts from citation logs, screenshots, or dashboards.
What must not be flattened
The following distinctions must remain visible:
- being cited is not yet being understood;
- not being cited is not yet being without effect;
- a visible source is not necessarily the governing source;
- citation frequency is not yet proof;
- a correct citation in one local case is not yet cross-system stability.
Recommended reading path
- AI citation analysis
- Being cited is not being understood
- Proof of fidelity: why a citation is no longer enough
- Representation gap
- Representation gap audit
Closing rule
On this site, citation makes a source visible; faithful understanding requires that its object, limits, and authority remain governing inside the answer.