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.
Cited source vs structuring source vs governing source
This page clarifies a decisive distinction for reading AI answers correctly: the source one sees, the source that structures the possible answer, and the source that ultimately governs the reconstruction are not always the same.
Those three thresholds may converge. They may also diverge sharply. That divergence is precisely what explains why an apparently well-sourced answer can still remain badly framed.
Why the confusion keeps returning
As soon as an answer displays an official source, the temptation is strong to conclude that the authority problem has been solved.
That shortcut is convenient. It remains insufficient.
A source may be visible without being structuring. A source may be structuring without remaining displayed. A source may be displayed and even useful while still losing, at the decisive moment, the normative framing of the answer.
In other words, the question is not only “which source is cited?”. The question becomes: which source changes the shape of the possible answer, and which source actually ends up governing the object, perimeter, and limits?
What the cited source correctly names
The cited source is the source visible in the final rendering.
It may take the form of:
- an explicitly mentioned domain;
- a visible link;
- a reference the user can see or open;
- an apparent support of legitimacy.
The cited source is therefore first a surface of documentary visibility.
It shows that a source is mobilizable and salient enough to appear. It does not yet show that it structured the answer, nor that it still governs the final perimeter.
What the structuring source adds
The structuring source adds a deeper level.
It is the source whose retrieval changes the shape of the possible answer. It does not merely add a local fact. It changes:
- the retained category;
- the type of comparison considered admissible;
- the regime of validity;
- the relationships between entities;
- the set of attributes that can now be mobilized.
At that level, the source may remain invisible in the final rendering.
That is precisely the issue covered by Structural visibility: a source acts not because it is shown, but because it changes the synthesis that becomes possible.
What the governing source adds beyond that
The governing source is the most demanding threshold of the three.
It is the source, or set of sources, whose authority ultimately prevails when the answer arbitrates:
- the applicable perimeter;
- exclusions and negations;
- the modality of the statement;
- the priority between contradictory sources;
- the boundary between what may be reused and what should no longer be inferred.
The governing source is therefore not merely a useful source. It is the source whose logic ends up bounding the answer.
At that level, the problem reaches the Authority boundary, Proof of fidelity, and often the Canon-output gap.
Four dissociations that must be learned
1. The cited source is not the structuring source
An answer may display the official site while a comparator, directory, or third-party listing imposed the category, comparison, or dominant attribute.
2. The structuring source is not the governing source
A source may open a space of possible answers without ultimately imposing the limits that should govern the final wording. Structure passes, but normative authority does not.
3. The governing source is not displayed
A source may fail to appear in the rendering while still remaining the source whose exclusions, relations, or regime of validity actually prevailed.
4. The same source may occupy a different role depending on the system
An official source may be cited, structuring, and governing in one system, yet only cited or only structuring in another. Role stability should never be presumed without protocol.
Reading rule applied on this site
On this site, the rule is simple:
- use cited source for explicit visibility in the answer;
- use structuring source when retrieving a source changes the regime of possible synthesis;
- use governing source when its authority actually bounds the perimeter, limits, and modality of the answer;
- use AI citation analysis when the investigation starts from visible outputs;
- use AI source mapping when the real distribution of roles must be qualified;
- use audit when the issue becomes probative, comparative, or corrective.
What must no longer be flattened
The following distinctions must remain explicit:
- a cited source is not yet a governing source;
- a structuring source may remain silent;
- a governing source may be a third party rather than the official source;
- citation frequency alone does not reveal the hierarchy of authority;
- one correct local citation does not prove stability in the source’s role.
Recommended reading path
- AI source mapping
- When the cited source is not the governing source
- Being cited vs being understood
- Structural visibility
- Authority boundary
- Representation gap audit
Closing rule
On this site, the displayed source is not enough to qualify the real authority of an answer: one must still know which source structures the possible synthesis, and then which source actually governs its boundaries.