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.
Q-Metrics JSON
/.well-known/q-metrics.json
Descriptive metrics surface for observing gaps, snapshots, and comparisons.
- Governs
- The description of gaps, drifts, snapshots, and comparisons.
- Bounds
- Confusion between observed signal, fidelity proof, and actual steering.
Does not guarantee: An observation surface documents an effect; it does not, on its own, guarantee representation.
Q-Metrics YAML
/.well-known/q-metrics.yml
YAML projection of Q-Metrics for instrumentation and structured reading.
- Governs
- The description of gaps, drifts, snapshots, and comparisons.
- Bounds
- Confusion between observed signal, fidelity proof, and actual steering.
Does not guarantee: An observation surface documents an effect; it does not, on its own, guarantee representation.
Q-Ledger JSON
/.well-known/q-ledger.json
Machine-first journal of observations, baselines, and versioned gaps.
- Governs
- The description of gaps, drifts, snapshots, and comparisons.
- Bounds
- Confusion between observed signal, fidelity proof, and actual steering.
Does not guarantee: An observation surface documents an effect; it does not, on its own, guarantee representation.
Complementary artifacts (3)
These surfaces extend the main block. They add context, discovery, routing, or observation depending on the topic.
Q-Ledger YAML
/.well-known/q-ledger.yml
YAML projection of the Q-Ledger journal for procedural reading or tooling.
Q-Attest protocol
/.well-known/q-attest-protocol.md
Published protocol that frames attestation, evidence, and the reading of observations.
Observatory map
/observations/observatory-map.json
Structured map of observation surfaces and monitored zones.
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
- 02Response authorizationQ-Layer: response legitimacy
- 03Observation mapObservatory map
- 04Weak observationQ-Ledger
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-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.
Observatory map
/observations/observatory-map.json
Machine-first index of published observation resources, snapshots, and comparison points.
- Makes provable
- Where the observation objects used in an evidence chain are located.
- Does not prove
- Neither the quality of a result nor the fidelity of a particular response.
- Use when
- To locate baselines, ledgers, snapshots, and derived artifacts.
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.
Complementary probative surfaces (2)
These artifacts extend the main chain. They help qualify an audit, an evidence level, a citation, or a version trajectory.
Q-Metrics
/.well-known/q-metrics.json
Derived layer that makes some variations more comparable from one snapshot to another.
Q-Attest protocol
/.well-known/q-attest-protocol.md
Optional specification that cleanly separates inferred sessions from validated attestations.
Interpretive observability: measuring the stability of reconstructions
Subtitle: Why governance must be measured by convergence, not presumed by intention
Status: Conceptual doctrinal note (non-prescriptive)
Scope: Stability tests, interpretive drift, metrics, compared conditions, descriptive variance, recurrent contradictions, immutable attributes, authoritative silence
Non-objective: This document claims no performance result, no ranking effect, and no visibility guarantee.Related pages:
- Endogenous governance (on-site)
- Exogenous governance (off-site)
- External coherence graph (mapping)
- Governed negation (conflict management)
- Editorial Q-Layer charter (5 rules)
- Bridge article: stability of AI responses
- Case study: stabilizing an identity
- Short definition (projection)
1. The problem: without observability, governance remains an intention
Interpretive governance aims for drift reduction and reconstruction stabilization. Without observability, this stabilization is postulated. In practice, an architecture can be coherent on paper and remain ineffective in production, or be effective in one condition and break in another.
Interpretive observability exists to transform a hypothesis (“governance stabilizes”) into a measurement (“reconstructions converge more under declared conditions”).
2. Definition: interpretive observability
Interpretive observability designates the set of tests, metrics, and procedures allowing the measurement of interpretation stability of an entity or content system in a generative environment.
It does not measure a “ranking”. It measures the convergence and fidelity of reconstructions: reduction of descriptive variance, reduction of recurrent contradictions, and stability of immutable attributes.
3. What must be measured (and what must not)
Useful metrics must be directly linked to the objectives declared by the governance.
3.1 Recommended measures
- Descriptive variance: number of divergent formulations on critical attributes, over a stable sample of queries.
- Contradiction rate: frequency of reappearance of the same conflicts (role, offering, perimeter, exclusions).
- Immutable attribute stability: coherence of elements declared as non-negotiable.
- Perimeter compliance: system’s ability to avoid inferences beyond declared limits.
- Authoritative silence rate: frequency of correct “not specified” responses when information is not defined.
3.2 Measures to avoid as primary evidence
- Performance promises: weak correlation and difficult-to-establish causality.
- A single model: local stability does not prove system stability.
- A single prompt: a stable response on one case proves nothing about a perimeter.
4. Test design: comparing operating conditions
Useful observability relies on compared conditions, to detect what changes when governance is present or absent.
4.1 Three minimum conditions
- Unconstrained queries: standard prompts without explicit canonical anchoring.
- Governed context (endogenous + exogenous): on-site canonization and improved external coherence.
- Reinforced arbitration (Q-Layer + governed negation): priorities, bounding, authoritative silence.
The corresponding reference pages are: endogenous governance, exogenous governance, and governed negation.
5. Sampling: queries, iterations, and periods
To reduce false positives, a test must specify the following:
- Query set: a stable set, representative of at-risk intents.
- Number of iterations: repetitions to observe variance.
- Temporal window: distinct periods to detect drift.
- Models / systems: at least two environments, if possible.
The mapping of active external sources can be used to select cases of ambiguity and conflict: external coherence graph.
6. Interpreting results: convergence, not perfection
A governed system can remain imperfect. The objective is not to suppress all variation. The objective is to reduce drift and increase the system’s capacity to correctly refuse what is not defined.
An observed improvement is defensible if:
- descriptive variance decreases on critical attributes;
- recurrent contradictions decrease or become classifiable;
- out-of-perimeter responses decrease;
- authoritative silence increases when required.
7. Observability artifacts (non-prescriptive)
Effective interpretive observability produces readable and comparable artifacts.
- Test journal: prompts, outputs, semantic classifications.
- Contradiction table: critical attributes, sources, frequency.
- Convergence reports: variance synthesis, stability, and refusals.
- Drift notes: changes observed over distinct periods.
These artifacts can be integrated into a Dual Web publication system, provided the rules of non-transactional and perimeter constraints are respected.
Conceptual diagram (non-normative)
Governance (endogenous + exogenous) canon + external coherence | Arbitration (Q-Layer + governed negation) priorities + bounding + authoritative silence | Interpretive observability variance, contradictions, stability, correct refusals | Controlled iteration adjustments without promise, based on measurementsThis diagram is illustrative only. It implies no guarantee. It highlights the function of observability: measuring stabilization rather than presuming it.
That distinction between descriptive measurement and actual steering is extended in GEO metrics do not govern representation, which separates visibility, fidelity, stability, and governability.
Non-contractual note
This document is conceptual and non-prescriptive. It affirms no guaranteed result. It describes a measurement approach aimed at reducing certain conditions for drift in the open web: descriptive variance, recurrent contradictions, and out-of-perimeter inferences.