Skip to content

Article

Context is not portable. Structure is.

In human publishing, context often carries authority. In machine interpretation, authority must be carried by structure if it is expected to survive reuse.

CollectionArticle
TypeArticle
Categorydynamiques interpretatives
Published2026-04-28
Updated2026-04-28
Reading time6 min

Governance artifacts

Governance files brought into scope by this page

This page is anchored to published surfaces that declare identity, precedence, limits, and the corpus reading conditions. Their order below gives the recommended reading sequence.

  1. 01Definitions canon
  2. 02Dual Web index
  3. 03Canonical AI entrypoint
Canon and identity#01

Definitions canon

/canon.md

Canonical surface that fixes identity, roles, negations, and divergence rules.

Governs
Public identity, roles, and attributes that must not drift.
Bounds
Extrapolations, entity collisions, and abusive requalification.

Does not guarantee: A canonical surface reduces ambiguity; it does not guarantee faithful restitution on its own.

Entrypoint#02

Dual Web index

/dualweb-index.md

Canonical index of published surfaces, precedence, and extended machine-first reading.

Governs
Access order across surfaces and initial precedence.
Bounds
Free readings that bypass the canon or the published order.

Does not guarantee: This surface publishes a reading order; it does not force execution or obedience.

Entrypoint#03

Canonical AI entrypoint

/.well-known/ai-governance.json

Neutral entrypoint that declares the governance map, precedence chain, and the surfaces to read first.

Governs
Access order across surfaces and initial precedence.
Bounds
Free readings that bypass the canon or the published order.

Does not guarantee: This surface publishes a reading order; it does not force execution or obedience.

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.

  1. 01
    Canon and scopeDefinitions canon
  2. 02
    Response authorizationQ-Layer: response legitimacy
  3. 03
Canonical foundation#01

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.
Legitimacy layer#02

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.
Artifact#03

interpretation-policy.json

/.well-known/interpretation-policy.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.

The hidden weakness of context

Human readers are excellent at using context.

They see the site. They understand the page hierarchy. They notice a heading, a warning, a publication date, a domain, a disclaimer, or a neighboring paragraph. A large part of authority is carried by the environment around the statement.

AI systems can use context too. But they do not always preserve it.

The moment content becomes a retrievable fragment, context starts to leak.

Why structure matters

Structure is the part of context that can travel.

A source hierarchy can travel. A canonical URL can travel. A machine-readable policy can travel. A declared definition, relation, negation, and response-legitimacy rule can travel better than a page impression.

This is the core difference between human publishing and machine interpretation.

For humans, context may be enough.

For AI systems, context must be converted into structure if authority is expected to survive.

Dual Web implication

This is one reason the Dual Web matters.

The human-facing layer can explain, persuade, nuance, and teach.

The machine-first layer must disambiguate, prioritize, bound, negate, route, and suspend.

Those two layers do not replace each other. They carry different parts of authority.

The risk of inferred authority

When structure is missing, the system does not stop interpreting. It infers authority from weaker signals: salience, wording, ranking, frequency, or apparent expertise.

That may produce a plausible answer. It may also misplace the source that should govern the answer.

Closing rule

In human publishing, authority is often carried by context. In machine interpretation, authority must be carried by structure.