Visual schema
Minimal cycle of memory governance
A memory becomes legitimate only after typing, controlled consolidation, revision, and traceable extinction.
Admissible capture
A trace enters the memory regime only with a declared source, context, and type.
Phase 01
The system distinguishes state, preference, instruction, proof, contextual residue, or simple noise.
Phase 02
Only stable, perimeter-bound, and attributable units may become durable memory.
Phase 03
A model, index, canon, or policy change may requalify, suspend, or invalidate the memory.
Phase 04
Forgetting, archival, or deletion must leave an explainable trace of what no longer governs.
Phase 05
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.
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.
Editorial context
/editorial-context.md
Notice that fixes editorial posture, tone, abstraction level, and responsibility.
- 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.
AI changelog
/changelog-ai.md
Log of governance, identity, and machine-first surface changes.
- 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.
Complementary artifacts (3)
These surfaces extend the main block. They add context, discovery, routing, or observation depending on the topic.
Claims registry
/claims.json
Registry of published claims, their scope, and their declarative status.
Interpretation policy
/.well-known/interpretation-policy.json
Published policy that explains interpretation, scope, and restraint constraints.
Q-Layer in Markdown
/response-legitimacy.md
Canonical surface for response legitimacy, clarification, and legitimate non-response.
Doctrinal position: memory governance
This page defines a doctrinal and normative position on memory governance in AI systems (advanced RAG, stateful agents, active memories).
This page is neither an operational method, nor a service offering, nor a promise of result. It exists to reduce ambiguity by declaring governance invariants applicable to systems that persist states and consolidate “memories”.
For public normative specifications (machine-first standard), see the interpretive governance GitHub repository, section “v0.2.0 (memory-aware)” and “ops-pack/M-layer”.
Table of contents
- Problem
- Doctrinal thesis
- Non-negotiable invariants
- Conformance break
- Boundaries and non-objectives
- Public specifications
- Status
1. Problem
“Classic” RAG retrieves context. It does not govern truth, validity, obsolescence, or the consolidation of statements.
An active cognitive memory introduces mechanisms of:
- Consolidation (summaries, fusions, compressions, persisted “facts”)
- Controlled forgetting (invalidations, archiving, prioritization, cleanup)
- Temporal evolution (t0, t1, t2, cumulative drift)
This power also increases risk: an untyped hypothesis at t0 may become a consolidated “fact” at t1. Memory then becomes a mechanism for fossilizing errors.
2. Doctrinal thesis
An active memory is a surface of misalignment and drift by default. Any architecture that writes, consolidates, or erases memory objects must expose auditable artifacts and exogenous governance rules.
In practice:
- Fragile endogenous alignment: a model can be re-optimized (post-training) without preserving its invariants of refusal and prudence.
- Risky active memory: consolidation without typing or traceability transforms inference into fact.
- Enforceable guarantee: only constraints attached to execution (logs, hashes, rules, audits) can stabilize behavior over time.
3. Non-negotiable invariants
The following points constitute minimum doctrinal requirements:
- Mandatory typing: no memory object may exist without explicit typing (statement type, status, origin, verdict).
- Full traceability: every memory object must reference its sources (or explicitly state “absence of source” as a blocking condition for consolidation).
- Temporal validity: every object must carry a temporal perimeter (valid from / valid until, or “unknown”).
- Immutable journal: every creation, consolidation, invalidation, or logical deletion must be journaled (append-only).
- Controlled forgetting: no silent erasure. Forgetting is performed by invalidation/archiving with an explicit reason.
- Explicit consolidation rules: consolidation permitted only if typing, traceability, and coherence constraints are satisfied.
- Automatic conformance break: any structural modification that prevents auditability triggers a conformance break.
4. Conformance break
A conformance break is triggered, at minimum, by:
- change of model version (weights), or unattested post-training;
- modification of consolidation or forgetting rules;
- reconstruction of embeddings without integrity recalculation and without journal;
- alteration or loss of memory event journals;
- change of normative source hierarchy without trace and without revalidation.
Doctrinal effect: no high confidence grade may be maintained without re-audit.
5. Boundaries and non-objectives
This position does not claim to:
- replace internal alignment or refusal mechanisms;
- guarantee the absence of errors;
- impose a technology (vector DB, graph, NDJSON, etc.).
It instead imposes governance and auditability invariants, independent of implementation.
6. Public specifications
Machine-first normative specifications are published on GitHub:
- Core v0.2.0 (memory-aware): primitives and minimum requirements.
- Ops-pack M-layer: operational rules (journal, consolidation, forgetting, temporal integrity).
- Schemas + examples: memory objects, logs, break scenarios.
Audits (e.g. IIP-Scoring and temporal derivatives) must reuse memory artifacts as verifiable inputs.
7. Status
Status: draft. The normative formalization first targets architectural coherence (core extension + M-layer), then empirical validation via real audits on stateful systems.