Skip to content

Definition

Source hierarchy

Canonical definition of source hierarchy: the declared ordering of canonical, derivative, contextual, outdated, contradictory and inadmissible sources for AI interpretation.

CollectionDefinition
TypeDefinition
Version1.0
Stabilization2026-05-07
Published2026-05-07
Updated2026-05-07

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
    Weak observationQ-Ledger
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.
Observation ledger#03

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.

Source hierarchy

This page is the canonical definition for source ordering inside the interpretive governance corpus.

Source hierarchy is the priority structure that determines which sources can authorize, qualify, constrain or invalidate an AI-generated answer.

Short definition

Source hierarchy is the priority structure that determines which sources can authorize, qualify, constrain or invalidate an AI-generated answer.

Why it matters

Retrieval is not authority. A system may retrieve official pages, third-party summaries, old versions, reviews, social fragments and generated descriptions in the same context window. Without source hierarchy, it can average them, smooth them or choose the most semantically salient source instead of the most authoritative one.

This is why the term belongs in the interpretive governance lexicon rather than in a generic SEO, analytics or monitoring vocabulary. The concern is not merely whether a page is visible. The concern is whether a system can reconstruct the correct meaning, assign the right authority to the right source and expose uncertainty when the available evidence does not justify a clean answer.

What it is not

A source hierarchy is not a sitemap, a list of important pages or a generic instruction to use official sources first. It must specify what happens when sources contradict each other, when a useful source is not authoritative and when historical material remains visible after correction.

The distinction is important for search strategy. A support article can explain the concept, a hub can organize the cluster and a framework can apply the concept, but this page is the canonical definition. Internal links should therefore point to Source hierarchy when the term itself is introduced.

Common failure modes

  • canonical and derivative sources are treated as equivalent;
  • an outdated page keeps version power;
  • a third-party description is easier to parse than the official canon;
  • contradictions are hidden by synthesis;
  • a source is used beyond its authority boundary.

These failure modes are not edge cases. They are normal outputs of systems that compress evidence, arbitrate between sources and answer under uncertainty without an explicit governance layer.

Governance implication

A serious corpus should label canonical, supporting, derivative, contextual, historical, contradictory and excluded sources. Internal links and machine-readable artifacts should reinforce that ordering.

For SERP ownership, the same rule applies editorially. The site should not allow several pages to compete silently for the same term. Hubs, categories, articles and service pages should name this surface as the primary definition, then use more specialized pages for applications, cases and methods.

Supporting surfaces

Phase 2 adjacency: from hierarchy to ordering

Source hierarchy becomes enforceable only when it is converted into authority ordering. A hierarchy lists classes of sources; ordering decides which source governs a claim when several sources are visible, admissible, old, contextual or contradictory.

Without this second movement, an AI system can still retrieve the right corpus and produce unauthorized synthesis by letting a contextual source govern a conclusion. The hierarchy must therefore be connected to the interpretive perimeter, authority conflict and mandatory silence.