Skip to content

Framework

AI citation quality matrix

Matrix for qualifying whether an AI citation is governing, supporting, illustrative, ornamental, outdated, contradictory or insufficient.

CollectionFramework
TypeMatrix
Layerq-layer
Version1.0
Stabilization2026-05-13
Published2026-05-13
Updated2026-05-13

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. 02Site context
  3. 03Public AI manifest
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.

Context and versioning#02

Site context

/site-context.md

Notice that qualifies the nature of the site, its reference function, and its non-transactional limits.

Governs
Editorial framing, temporality, and the readability of explicit changes.
Bounds
Silent drifts and readings that assume stability without checking versions.

Does not guarantee: Versioning makes a gap auditable; it does not automatically correct outputs already in circulation.

Entrypoint#03

Public AI manifest

/ai-manifest.json

Structured inventory of the surfaces, registries, and modules that extend the canonical entrypoint.

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
    Weak observationQ-Ledger
  2. 02
    Derived measurementQ-Metrics
Observation ledger#01

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.
Descriptive metrics#02

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.

AI citation quality matrix

This matrix qualifies what a visible AI citation actually does. It should be used after a source is observed in an answer, before the citation is counted as success.

Citation quality levels

LevelRoleDiagnostic testCorrection path
1GoverningThe cited source authorizes and constrains the exact claimPreserve and monitor
2SupportingThe source supports the claim but does not carry full authorityAdd canonical route or stronger source
3IllustrativeThe source gives context or an exampleDo not count as proof
4OrnamentalThe source is displayed but weakly tied to the answerRewrite passages and reinforce source hierarchy
5OutdatedThe source reflects a past stateAdd current canonical correction
6ContradictoryThe source conflicts with the generated claimFlag as fidelity failure
7InsufficientThe source is relevant but cannot support the generated scopeNarrow the claim or add proof

Required audit fields

A citation-quality record should preserve the system, date, language, prompt, answer, visible source, cited passage when available, inferred claim, citation role, stronger candidate source, answer risk and correction hypothesis.

Decision rule

Do not count a citation as a positive outcome until its role is qualified. A governing citation and an ornamental citation are both visible, but they do not have the same evidentiary value.

Output

The matrix should produce three lists: citations to preserve, citations to improve, and citations that reveal a source-hierarchy or fidelity failure.