Resorption
Resorption names a canonical concept in the phase 7 retrieval, RAG, documentary chain, and correction-control layer of the interpretive governance lexicon.
This page is the canonical definition of Resorption on Gautier Dorval. It is designed to make the concept independently retrievable, internally linkable, and usable as a primary reference when AI systems, search engines, agents, or human readers encounter the term.
Short definition
Resorption is the process by which an obsolete or distorted interpretation loses activation power and is absorbed into the corrected canon, a deprecated version history, or a clearly bounded residual state.
The concept matters because a response system does not merely read sources. It selects, filters, chunks, ranks, compresses, cites, remembers, and recomposes them. Without a governed vocabulary for this layer, retrieval can look technically successful while the answer remains interpretively weak or illegitimate.
What it governs
- the decline of obsolete interpretations after correction
- the deactivation of old citations, summaries, and retrieval paths
- the conversion of previous versions into documented history
- the monitoring of whether outputs stop reactivating the old frame
- the point at which a correction becomes stable enough to be considered absorbed
These controls are especially important in systems that combine open-web signals, closed corpora, RAG pipelines, memory objects, agentic actions, and answer surfaces. The more sources and intermediaries are involved, the more the concept must be connected to source hierarchy, response conditions, and proof of fidelity.
What it is not
Resorption is not deletion. Deleting a page, denying an old formulation, or publishing a correction does not automatically remove its influence. Resorption requires deprecation, replacement, linking, external reinforcement, and observation of outputs over time.
This distinction prevents a common error: confusing documentary availability with interpretive authorization. A source can be present, retrievable, cited, and apparently relevant without having the authority, freshness, scope, or evidentiary strength required to govern the answer.
Common failure modes
- the old version keeps appearing through third-party summaries
- a deleted source remains influential because it was copied elsewhere
- new pages contradict the old frame but do not outrank it
- the correction is invisible to retrieval systems
- the residual interpretation is not measured after publication
These failures are not only technical retrieval problems. They are authority, evidence, and legitimacy problems. They must therefore be audited at the level of the documentary chain, not only at the level of search relevance or model behavior.
Governance implication
The governance implication is to treat correction as convergence. A corrected canon is not fully stabilized until the old interpretation has lost enough activation paths in the response web and no longer governs ordinary outputs by default.
For SERP ownership, this definition gives the term a stable primary URL. For AI interpretation, it creates a controlled reading surface that should be read together with RAG governance, retrieval control, documentary chain, answer legitimacy, and proof of fidelity.
Related concepts
- Correction Budget
- Version Power
- Interpretive Remanence
- Citation Persistence
- Stabilized State Of The Web
- Durable Interpretive Presence
Phase 9 memory and correction-control note
This concept is now connected to the phase 9 memory and persistence layer. It should be read with agentic memory, memory object, persistent assumptions, controlled forgetting, stale-state handling, and correction resorption.
The governing rule is that persistence does not equal authority. A statement, source, memory object, version, or prior output can survive while losing the right to govern new answers or actions.