Cognitive Memoisation: corpus guide: Difference between revisions

From publications
VisualWikitext
No edit summary
 
(28 intermediate revisions by the same user not shown)
Line 1: Line 1:
 
==metadata==
 
 
<font size=-2>
<font size=-2>
{|
{|
Line 8: Line 6:
|''Author'': || Ralph B. Holland  
|''Author'': || Ralph B. Holland  
|-
|-
| ''version'': || 1.1.0
| ''version'': || 2.0.0
|-
|-
| ''Publication Date'': ||  2025-12-23
| ''Publication Date'': ||  2025-12-22T19:10Z
|-
|-
| ''Update'':  || 2025-01-04T05:12 v1.1.0 renamed from "Cognitive Memoisation: A framework for human cognition" to "Cognitive Memoisation: corpus guide"
| ''Update'':  || 2026-01-13T19:09 new dimension table and two projections.<br/>2026-01-06T10:25Z v1.3.0 Includes the release of CM-2<br/>2025-01-04T05:12 v1.1.0 renamed from "Cognitive Memoisation: A framework for human cognition" to "Cognitive Memoisation: corpus guide"<br/>Include papers.
|-
|-
| ''Affiliation'': || Arising Technology Systems Pty Ltd
| ''Affiliation'': || Arising Technology Systems Pty Ltd
Line 24: Line 22:
| <br/>
| <br/>
|}
|}
== Metadata (Normative) ==
The metadata table immediately preceding this section is CM-defined and constitutes the authoritative provenance record for this MWDUMP artefact.
All fields in that table (including artefact, author, version, date, local timezone, and reason) MUST be treated as normative metadata.
The assisting system MUST NOT infer, normalise, reinterpret, duplicate, or rewrite these fields. 
If any field is missing, unclear, or later superseded, the change MUST be made explicitly by the human and recorded via version update, not inferred.
<blockquote>
This document predates its open licensing.
As curator and author, I apply the [https://www.apache.org/licenses/LICENSE-2.0.txt|'''Apache License, Version 2.0'''], at publication to permit reuse and implementation while preventing enclosure or patent capture. This licensing action does not revise, reinterpret, or supersede any normative content herein.
Authority remains explicitly human; no implementation, system, or platform may assert epistemic authority by virtue of this license.
(2025-12-18 version 1.0  - See the [[Main Page]])</blockquote>
</font>
</font>
<div style="break-before:page"></div>
<div style="break-before:page"></div>


Line 44: Line 57:
This document establishes the rationale, scope, and interpretive framework required to understand Cognitive Memoisation and its role in enabling human-centric knowledge workflows with stateless LLMs.
This document establishes the rationale, scope, and interpretive framework required to understand Cognitive Memoisation and its role in enabling human-centric knowledge workflows with stateless LLMs.


== Normative CM Paper References ==
= Cognitive Memoisation Corpus Map =


The following documents constitute the '''authoritative CM corpus'''. Titles are '''normative MediaWiki page names''' and must not be paraphrased.
== Canonical Dimension Table (Anchored) ==


* [[Cognitive Memoisation and LLMs: A Method for Exploratory Modelling Before Formalisation]] (Primary paper)
{| class="wikitable"
! Dim ID !! Canonical Dimension (verbatim) !! Scope Note
|-
| D1 || Statelessness and Memory Management in LLMs || LLM statelessness, safety, memory absence
|-
| D2 || Externalisation of Cognitive Artefacts || Durable external cognition
|-
| D3 || Round-Trip Knowledge Engineering (RTKE) || Re-ingestion, reuse, evolution
|-
| D4 || Dangling Cognates and Unresolved Cognition || Unfinished / provisional concepts
|-
| D5 || Constraints and Knowledge Integrity || Groundhog Day prevention
|-
| D6 || Human Curated Knowledge vs. Model State || Authority separation
|-
| D7 || Reflexive Development of Cognitive Memoisation (RTKE Case Study) || Self-referential development
|-
| D8 || Dangling Cognates as First-Class Cognitive Constructs || Formal DC elevation
|-
| D9 || ChatGPT UI Boundary Friction as a Constraint on RTKE || Platform limits
|-
| D10 || Plain-Language Accessibility and Public Framing || Reader-facing clarity
|-
| D11 || Governance, Authority, and Failure Modes || Control, breakdown, recovery
|-
| D12 || Client-side Memoisation (CM-2) || Mechanism disclosure
|}
 
== Time-Ordered Projection with Inline Dimensions ==
 
=== 2025-12-17 — FOUNDATION ===
* [[Progress Without Memory: Cognitive Memoisation as a Knowledge-Engineering Pattern for Stateless LLM Interaction]]
** D1 — Statelessness and Memory Management in LLMs
** D2 — Externalisation of Cognitive Artefacts
** D3 — Round-Trip Knowledge Engineering (RTKE)
** D5 — Constraints and Knowledge Integrity
** D6 — Human Curated Knowledge vs. Model State
 
=== 2025-12-18 — COMMUNICATION ===
* [[Cognitive Memoisation: Plain-Language Summary (For Non-Technical Readers)]]
* [[Cognitive Memoisation: Plain-Language Summary (For Non-Technical Readers)]]
* [[Progress Without Memory: Cognitive Memoisation as a Knowledge-Engineering Pattern for Stateless LLM Interaction]]
** D2 — Externalisation of Cognitive Artefacts
** D10 — Plain-Language Accessibility and Public Framing
 
=== 2025-12-28 — PORTABILITY / SEMANTICS ===
* [[Dangling Cognates: Preserving Unresolved Knowledge in Cognitive Memoisation]]
** D4 — Dangling Cognates and Unresolved Cognition
** D8 — Dangling Cognates as First-Class Cognitive Constructs
 
=== 2026-01-04 — MECHANISM / CORPUS ANCHOR ===
* [[Cognitive Memoisation and LLMs: A Method for Exploratory Modelling Before Formalisation]]
** D1 — Statelessness and Memory Management in LLMs
** D2 — Externalisation of Cognitive Artefacts
** D3 — Round-Trip Knowledge Engineering (RTKE)
** D4 — Dangling Cognates and Unresolved Cognition
** D5 — Constraints and Knowledge Integrity
** D6 — Human Curated Knowledge vs. Model State
 
* [[Cognitive Memoisation: Corpus Guide]]
** D1 — Statelessness and Memory Management in LLMs
** D2 — Externalisation of Cognitive Artefacts
** D3 — Round-Trip Knowledge Engineering (RTKE)
** D4 — Dangling Cognates and Unresolved Cognition
** D5 — Constraints and Knowledge Integrity
** D6 — Human Curated Knowledge vs. Model State
** D7 — Reflexive Development of Cognitive Memoisation (RTKE Case Study)
** D8 — Dangling Cognates as First-Class Cognitive Constructs
** D9 — ChatGPT UI Boundary Friction as a Constraint on RTKE
** D10 — Plain-Language Accessibility and Public Framing
** D11 — Governance, Authority, and Failure Modes
** D12 — Client-side Memoisation (CM-2)
 
* [[Journey: Human-Led Convergence in the Articulation of Cognitive Memoisation]]
** D1 — Statelessness and Memory Management in LLMs
** D2 — Externalisation of Cognitive Artefacts
** D3 — Round-Trip Knowledge Engineering (RTKE)
** D6 — Human Curated Knowledge vs. Model State
** D12 — Client-side Memoisation (CM-2)
 
=== 2026-01-05 — GOVERNANCE, UI, SYSTEMS ===
* [[Cognitive Memoisation for Governing Knowledge in Human–AI Collaboration]]
** D6 — Human Curated Knowledge vs. Model State
** D11 — Governance, Authority, and Failure Modes
** D12 — Client-side Memoisation (CM-2)
 
* [[ChatGPT UI Boundary Friction as a Constraint on Round-Trip Knowledge Engineering]]
* [[ChatGPT UI Boundary Friction as a Constraint on Round-Trip Knowledge Engineering]]
** D1 — Statelessness and Memory Management in LLMs
** D5 — Constraints and Knowledge Integrity
** D9 — ChatGPT UI Boundary Friction as a Constraint on RTKE
* [[Cognitive Memoisation: LLM Systems Requirements for Knowledge Round Trip Engineering]]
** D3 — Round-Trip Knowledge Engineering (RTKE)
** D5 — Constraints and Knowledge Integrity
* [[Why Cognitive Memoisation Is Not Memorization]]
** D10 — Plain-Language Accessibility and Public Framing
=== 2026-01-06 — FAILURE & RECOVERY ===
* [[From UI Failure to Logical Entrapment: A Case Study in Post-Hoc Cognitive Memoisation]]
** D9 — ChatGPT UI Boundary Friction as a Constraint on RTKE
** D11 — Governance, Authority, and Failure Modes
* [[XDUMP as a Minimal Recovery Mechanism for Round-Trip Knowledge Engineering Under Governance Situated Inference Loss]]
** D3 — Round-Trip Knowledge Engineering (RTKE)
** D11 — Governance, Authority, and Failure Modes
* [[Recent Breaking Change in ChatGPT: The Loss of Semantic Artefact Injection for Knowledge Engineering]]
** D9 — ChatGPT UI Boundary Friction as a Constraint on RTKE
** D11 — Governance, Authority, and Failure Modes
=== 2026-01-08 — REFLEXIVE & GOVERNANCE THEORY ===
* [[Reflexive Development of Cognitive Memoisation: A Round-Trip Cognitive Engineering Case Study]]
* [[Reflexive Development of Cognitive Memoisation: A Round-Trip Cognitive Engineering Case Study]]
** D3 — Round-Trip Knowledge Engineering (RTKE)
** D6 — Human Curated Knowledge vs. Model State
** D7 — Reflexive Development of Cognitive Memoisation (RTKE Case Study)
* [[Reflexive Development of Cognitive Memoisation: Dangling Cognates as a First-Class Cognitive Construct]]
* [[Reflexive Development of Cognitive Memoisation: Dangling Cognates as a First-Class Cognitive Construct]]
** D4 — Dangling Cognates and Unresolved Cognition
** D8 — Dangling Cognates as First-Class Cognitive Constructs
* [[Authority Inversion: A Structural Failure in Human–AI Systems]]
** D6 — Human Curated Knowledge vs. Model State
** D11 — Governance, Authority, and Failure Modes
=== 2026-01-10 to 2026-01-12 — SYNTHESIS & MYTH-BUSTING ===
* [[Nothing Is Lost: How to Work with AI Without Losing Your Mind]]
** D3 — Round-Trip Knowledge Engineering (RTKE)
** D10 — Plain-Language Accessibility and Public Framing
* [[Cognitive Memoisation Is Not Skynet]]
** D10 — Plain-Language Accessibility and Public Framing
* [[Lopping the Loop with No End in Sight: Circular Reasoning Under Stateless Inference Without Governance]]
** D1 — Statelessness and Memory Management in LLMs
** D11 — Governance, Authority, and Failure Modes


== Dimensions Addressed in This Paper ==
<!-- END OF MWDUMP -->
<!--
MWDUMP
Artefact: Cognitive Memoisation — Invariants Governing Corpus Dimension Tables and Projections
Author: Ralph B. Holland (curated read-back)
Status: Normative (organisational / projection-level)
Scope: Invariants governing the construction of corpus dimension tables and their projections
Note: These invariants DO NOT amend CM-1 or CM-2. They govern corpus mapping, indexing, and projection only.
-->


The following dimensions are key to understanding the problems that Cognitive Memoisation (CM) addresses, especially in the context of stateless Large Language Models (LLMs) and the human-managed preservation of cognitive state:
= Cognitive Memoisation: Corpus Mapping and Projection Invariants =


=== 1. Statelessness and Memory Management in LLMs ===
== Scope and Intent ==
'''Core Concept''': Addressing the statelessness of LLMs and the challenge of managing '''conceptual memory''' externally.
 
'''Dimension Addressed''': How can cognitive memory be maintained outside the LLM model to overcome statelessness, and how does CM provide this functionality while respecting LLM safety constraints? 
This artefact enumerates the complete set of invariants required to:
'''Relevant Papers''':
 
* [[Cognitive Memoisation and LLMs: A Method for Exploratory Modelling Before Formalisation]] (Primary paper)
* construct the canonical dimension table
* [[Progress Without Memory: Cognitive Memoisation as a Knowledge-Engineering Pattern for Stateless LLM Interaction]]
* assign dimensions to corpus artefacts
* [[ChatGPT UI Boundary Friction as a Constraint on Round-Trip Knowledge Engineering]]
* produce time-ordered projections
* produce divergence (dimension) projections
* preserve epistemic discipline, provenance, and human authority
 
These invariants apply to corpus organisation and projection only. 
They do not introduce new CM definitions, modify CM-master invariants, or assert governance over reasoning behaviour.
 
== Authority and Epistemic Position ==
 
* All invariants herein are human-authored and curator-governed.
* The assisting system MUST treat this artefact as binding for corpus mapping tasks when asserted.
* These invariants govern representation and organisation, not truth, correctness, or inference.
 
== Canonical Dimension Invariants ==
 
=== CM-CORPUS-INV-01 — Dimension Canonicality Invariant ===
 
Each dimension MUST have:
* a stable identifier (e.g. D1, D2, …)
* a single canonical name
* a stable semantic scope
 
Dimension identifiers and names MUST NOT be inferred, renamed, merged, split, or reordered by the assisting system.
 
=== CM-CORPUS-INV-02 — Dimension Vocabulary Closure Invariant ===
 
The set of dimensions is closed.
 
No additional dimensions may be introduced unless explicitly declared by the human curator.
 
Absence of coverage MUST be represented as absence, not as invention.
 
=== CM-CORPUS-INV-03 — Dimension Semantic Fidelity Invariant ===
 
Assignment of a dimension to an artefact MUST reflect explicit scope alignment present in the artefact itself or in curator-supplied mapping.
 
The assisting system MUST NOT infer dimension relevance based on stylistic similarity, topic proximity, or semantic guesswork.
 
== Artefact Identification Invariants ==
 
=== CM-CORPUS-INV-04 — Normative Title Fidelity Invariant ===
 
Artefacts MUST be referenced using their exact normative MediaWiki page titles.
 
Paraphrase, abbreviation, or normalisation of titles is prohibited.
 
=== CM-CORPUS-INV-05 — Artefact Identity Stability Invariant ===
 
An artefact is identified solely by its title and publication date.
 
Later editorial changes do not create new artefact identities unless explicitly versioned by the human.
 
== Temporal Ordering Invariants ==
 
=== CM-CORPUS-INV-06 — Declared Date Authority Invariant ===
 
Time ordering MUST use the declared publication date as supplied by the human curator.
 
The assisting system MUST NOT infer, estimate, or correct dates.
 
If multiple dates exist, the curator MUST specify which date governs ordering.
 
=== CM-CORPUS-INV-07 — Sequence Over Precision Invariant ===
 
Temporal sequence is authoritative even if time precision is coarse.
 
Relative ordering MUST be preserved even when exact timestamps are unavailable.
 
== Projection Construction Invariants ==
 
=== CM-CORPUS-INV-08 — Projection Non-Inference Invariant ===
 
Projections MUST NOT introduce:
* new artefacts
* new dimensions
* new relationships
* new interpretations
 
A projection is a re-expression of existing assignments only.
 
=== CM-CORPUS-INV-09 — Projection Completeness Invariant ===
 
Within declared scope, projections MUST include all eligible artefacts.
 
Selective omission constitutes a projection violation.
 
=== CM-CORPUS-INV-10 — Multi-Projection Consistency Invariant ===
 
All projections MUST be semantically consistent with one another.
 
Differences between projections may exist only in ordering or grouping, not in content.
 
== Time-Ordered Projection Invariants ==
 
=== CM-CORPUS-INV-11 — Time-Ordered Projection Structure Invariant ===
 
A time-ordered projection MUST:
 
* group artefacts by declared date
* list artefacts within each group
* attach dimensions as subordinate information
 
Time is the primary axis; dimensions are secondary.
 
=== CM-CORPUS-INV-12 — Inline Dimension Expansion Invariant ===
 
When dimensions are listed under artefacts:
 
* each dimension MUST include both identifier and full canonical name
* users MUST NOT be required to consult a separate table to understand dimension meaning
 
== Divergence (Dimension) Projection Invariants ==
 
=== CM-CORPUS-INV-13 — Dimension-Centric Projection Structure Invariant ===
 
A divergence projection MUST:
 
* use dimensions as the primary axis
* list all artefacts participating in each dimension
* preserve publication dates for temporal context
 
=== CM-CORPUS-INV-14 — Non-Exclusivity Invariant ===
 
Artefacts MAY appear under multiple dimensions.
 
Multiplicity is expected and MUST NOT be collapsed.
 
== Representation and Emission Invariants ==
 
=== CM-CORPUS-INV-15 — MediaWiki-Only Emission Invariant ===
 
All corpus projections emitted as MWDUMP MUST use MediaWiki syntax exclusively.
 
Markdown, hybrid markup, or implicit formatting is prohibited.
 
=== CM-CORPUS-INV-16 — Bullet Level Semantics Invariant ===
 
Bullet depth conveys semantic hierarchy:
 
* one asterisk (*) — artefact
** two asterisks (**) — dimension assignment
*** three asterisks (***) — sub-dimension or note (if present)
**** four asterisks (****) — reserved
 
The assisting system MUST respect bullet depth semantics.
 
== Human Readability and Governance Invariants ==


=== 2. Externalisation of Cognitive Artefacts ===
=== CM-CORPUS-INV-17 — Human Readability Invariant ===
'''Core Concept''': The process of externalising concepts, facts, inferences, and unresolved cognition into structured, durable formats. 
'''Dimension Addressed''': How can cognitive content be externalised and stored in a manner that ensures its continued use across sessions, without being lost due to session termination or model limitations? 
'''Relevant Papers''':
* [[Cognitive Memoisation and LLMs: A Method for Exploratory Modelling Before Formalisation]] (Primary paper)
* [[Progress Without Memory: Cognitive Memoisation as a Knowledge-Engineering Pattern for Stateless LLM Interaction]]
* [[Cognitive Memoisation: Plain-Language Summary (For Non-Technical Readers)]]


=== 3. Round-Trip Knowledge Engineering (RTKE) ===
Corpus projections MUST be intelligible to human readers without external tooling.
'''Core Concept''': The cyclical process of taking externalised cognitive artefacts, reintegrating them into reasoning processes, and ensuring that knowledge evolves without loss.
'''Dimension Addressed''': How can externalised knowledge be reused, refined, and preserved over time through iterative processes, and how does CM facilitate this while maintaining consistency? 
'''Relevant Papers''':
* [[Cognitive Memoisation and LLMs: A Method for Exploratory Modelling Before Formalisation]] (Primary paper)
* [[Progress Without Memory: Cognitive Memoisation as a Knowledge-Engineering Pattern for Stateless LLM Interaction]]
* [[Reflexive Development of Cognitive Memoisation: A Round-Trip Cognitive Engineering Case Study]]


=== 4. Dangling Cognates and Unresolved Cognition ===
Abbreviation without expansion is prohibited.
'''Core Concept''': Managing cognitive elements that are under construction or incomplete, allowing them to participate in reasoning without forcing premature resolution.
'''Dimension Addressed''': How can unresolved cognitive elements (Dangling Cognates) be preserved, tracked, and used safely in ongoing reasoning, without prematurely solidifying them? 
'''Relevant Papers''':
* [[Reflexive Development of Cognitive Memoisation: Dangling Cognates as a First-Class Cognitive Construct]]
* [[Cognitive Memoisation and LLMs: A Method for Exploratory Modelling Before Formalisation]] (Primary paper)


=== 5. Constraints and Knowledge Integrity ===
=== CM-CORPUS-INV-18 — No Implied Authority Invariant ===
'''Core Concept''': Defining and applying constraints to preserve the integrity of cognitive memory and prevent “Groundhog Day” rediscovery. 
'''Dimension Addressed''': How can constraints be implemented to ensure that knowledge persists across sessions without redundancy, and how can it be efficiently reused? 
'''Relevant Papers''':
* [[ChatGPT UI Boundary Friction as a Constraint on Round-Trip Knowledge Engineering]]
* [[Progress Without Memory: Cognitive Memoisation as a Knowledge-Engineering Pattern for Stateless LLM Interaction]]
* [[Cognitive Memoisation and LLMs: A Method for Exploratory Modelling Before Formalisation]] (Primary paper)


=== 6. Human Curated Knowledge vs. Model State ===
Presence of an artefact or dimension in a projection MUST NOT be interpreted as endorsement, priority, or correctness.
'''Core Concept''': Differentiating between human-curated knowledge and LLM model state, ensuring that cognitive memory and decision-making remain under human control.
'''Dimension Addressed''': How can the human maintain full authority over cognitive content while ensuring that the stateless nature of LLMs is respected? 
'''Relevant Papers''':
* [[Progress Without Memory: Cognitive Memoisation as a Knowledge-Engineering Pattern for Stateless LLM Interaction]]
* [[Reflexive Development of Cognitive Memoisation: A Round-Trip Cognitive Engineering Case Study]]
* [[Cognitive Memoisation and LLMs: A Method for Exploratory Modelling Before Formalisation]] (Primary paper)


=== 7. Reflexive Development of Cognitive Memoisation: A Round-Trip Cognitive Engineering Case Study ===
Organisation does not imply evaluation.


'''Core Concept''': CM supports '''reflexive development''', where knowledge evolves iteratively through '''Round-Trip Knowledge Engineering (RTKE)'''. This process involves the '''externalisation''', '''elaboration''', and '''refinement''' of cognitive artefacts over time.
== Change and Evolution Invariants ==
<br/>'''Dimension addressed''': How does '''CM''' facilitate the '''continuous refinement of conceptual memory''' by allowing the '''re-integration''' of externalised cognitive artefacts, ensuring that knowledge development is adaptive and flexible?


*  [[Reflexive Development of Cognitive Memoisation: A Round-Trip Cognitive Engineering Case Study]]
=== CM-CORPUS-INV-19 — Explicit Change Invariant ===


=== 8. Reflexive Development of Cognitive Memoisation: Dangling Cognates as a First-Class Cognitive Construct ===
Any change to:


'''Core Concept''': '''Dangling Cognates''', which are incomplete or evolving concepts, are treated as '''first-class cognitive constructs''' in '''CM'''. These cognitive elements are preserved and elaborated over time to allow for '''continuous cognitive development'''.
* dimension set
<br/>'''Dimension Addressed''': How can '''CM''' manage and preserve '''Dangling Cognates''', enabling humans to work with '''unresolved cognition''' and progressively refine and solidify these concepts across sessions without losing continuity?
* dimension definitions
* artefact–dimension assignments
* projection rules


* [[Reflexive Development of Cognitive Memoisation: Dangling Cognates as a First-Class Cognitive Construct]]
MUST be explicitly declared by the human curator.


=== 9. ChatGPT UI Boundary Friction as a Constraint on Round-Trip Knowledge Engineering ===
Silent drift is prohibited.


'''Core Concept''': The '''statelessness''' of '''LLMs''', such as '''ChatGPT''', leads to '''boundary friction''' in '''Round-Trip Knowledge Engineering (RTKE)'''. '''LLMs''' do not retain memory across sessions, which causes '''knowledge loss''' between interactions.
=== CM-CORPUS-INV-20 — Backward Compatibility Invariant ===


'''Dimension Addressed:''' How can '''Cognitive Memoisation (CM)''' mitigate the friction caused by the stateless nature of '''LLMs''' by enabling the '''externalisation''' of cognitive artefacts, ensuring continuity of reasoning and the '''preservation of insights''' over time?
Existing projections remain valid historical artefacts unless explicitly superseded.
* [[ChatGPT UI Boundary Friction as a Constraint on Round-Trip Knowledge Engineering]]


== 10. Additional corpus papers not yet covered (verbatim titles) ==
New projections MUST NOT retroactively invalidate prior ones.


The following CM corpus papers are referenced in ''Cognitive Memoisation: corpus guide'' but are not yet covered by the current Journey paper references set. Each entry below provides a short, descriptive statement of what the paper contributes.
== Summary for Human Readers ==


* [[Cognitive Memoisation: corpus guide]]
These invariants exist to ensure that the Cognitive Memoisation corpus:
** Primary introduction and conceptual anchor for the CM corpus. Establishes rationale, scope, and interpretive framing; enumerates the authoritative corpus papers and maps them to key dimensions (statelessness, externalisation, RTKE, Dangling Cognates, constraints, and human authority).


* [[Cognitive Memoisation: Plain-Language Summary (For Non-Technical Readers)]]
* remains navigable as it grows
** A non-technical entry point to CM intended for accessibility. Provides a simplified conceptual explanation of CM’s purpose, core mechanisms, and human-governed stance without requiring knowledge-engineering or LLM systems terminology.
* can be read chronologically or thematically without confusion
* preserves human authority over meaning and structure
* avoids accidental reinterpretation by tooling or automation


* [[Reflexive Development of Cognitive Memoisation: Dangling Cognates as a First-Class Cognitive Construct]]
They formalise how maps are drawn — not what the territory means.
** A focused methodological paper on unresolved cognition: formalises Dangling Cognates as first-class constructs and explains how CM preserves, carries, and elaborates unresolved elements across Round-Trip Knowledge Engineering cycles without premature settlement.


== 11. Corpus alignment notes for Journey ==
== Summary for Assisting Systems ==


* The Journey paper already aligns strongly with the corpus guide’s “dimensions” framing, especially:
When constructing corpus tables or projections:
** Statelessness and Memory Management in LLMs
** Externalisation of Cognitive Artefacts
** Round-Trip Knowledge Engineering (RTKE)
** Human Curated Knowledge vs. Model State
* The missing coverage above fills two gaps:
** An explicit “reader-facing” bridge paper (Plain-Language Summary)
** A DC-specific deepening paper (Dangling Cognates as first-class construct)
* The corpus guide itself provides the canonical map of the corpus and is suitable as an explicit anchor reference for the Journey paper’s positioning.


== Categories (appropriate additions) ==
* do not invent
* do not infer
* do not optimise
* do not rename
* do not omit


Rearrange only what is already governed.
== categories ==
[[Category:Cognitive Memoisation]] [[Category:Durable Knowledge]]
[[Category:Cognitive Memoisation]]
[[Category:Cognitive Memoisation]]
[[Category:Corpus Guides]]
[[Category:Corpus Guides]]
Line 161: Line 426:
[[Category:Epistemic Governance]]
[[Category:Epistemic Governance]]
[[Category:Human–LLM Interaction]]
[[Category:Human–LLM Interaction]]
[[category:LLM]]
[[category:LLM]]
[[category:ChatGPT]]
[[Category:Cognitive Memoisation]]
[[Category:Knowledge Engineering]]
[[Category:Human–AI Interaction]]
[[Category:Stateless Systems]]
[[Category:Cognitive Memoisation]]
[[Category:Knowledge Engineering]]
[[Category:Human–AI Interaction]]
[[Category:Stateless Systems]]
[[Category:Cognitive Memoisation]]
[[Category:Knowledge Engineering]]
[[Category:Human–AI Interaction]]
[[Category:Stateless Systems]]
[[Category:Stateless Systems]]
[[category:Ralph Holland:AI Publications]]
[[category:Ralph Holland:AI Publications]]
[[category:memoisation]]
[[category:memoisation]]
[[category:public]]
[[category:public]]
=categories=
[[category:LLM]]
[[category:LLM]]
[[category:ChatGPT]]
[[category:ChatGPT]]
[[Category:Cognitive Memoisation]]
[[Category:Knowledge Engineering]]
[[Category:Human–AI Interaction]]
[[Category:Stateless Systems]]
[[Category:Cognitive Memoisation]]
[[Category:Knowledge Engineering]]
[[Category:Human–AI Interaction]]
[[Category:Stateless Systems]]
[[Category:Cognitive Memoisation]]
[[Category:Knowledge Engineering]]
[[Category:Human–AI Interaction]]
[[Category:Human–AI Interaction]]
[[Category:Stateless Systems]]
[[Category:Stateless Systems]]

Latest revision as of 20:10, 13 January 2026

metadata

Title: Cognitive Memoisation: corpus guide.
Author: Ralph B. Holland
version: 2.0.0
Publication Date: 2025-12-22T19:10Z
Update: 2026-01-13T19:09 new dimension table and two projections.
2026-01-06T10:25Z v1.3.0 Includes the release of CM-2
2025-01-04T05:12 v1.1.0 renamed from "Cognitive Memoisation: A framework for human cognition" to "Cognitive Memoisation: corpus guide"
Include papers.
Affiliation: Arising Technology Systems Pty Ltd
Contact: ralph.b.holland [at] gmail.com
Provenance: This is an authored paper maintained as a MediaWiki document as part of the category:Cognitive Memoisation corpus.
Status: final =

Metadata (Normative)

The metadata table immediately preceding this section is CM-defined and constitutes the authoritative provenance record for this MWDUMP artefact.

All fields in that table (including artefact, author, version, date, local timezone, and reason) MUST be treated as normative metadata.

The assisting system MUST NOT infer, normalise, reinterpret, duplicate, or rewrite these fields. If any field is missing, unclear, or later superseded, the change MUST be made explicitly by the human and recorded via version update, not inferred.

This document predates its open licensing.

As curator and author, I apply the Apache License, Version 2.0, at publication to permit reuse and implementation while preventing enclosure or patent capture. This licensing action does not revise, reinterpret, or supersede any normative content herein.

Authority remains explicitly human; no implementation, system, or platform may assert epistemic authority by virtue of this license.

(2025-12-18 version 1.0 - See the Main Page)

Cognitive Memoisation: corpus guide.

Introductory Position

This paper serves as the primary introduction and conceptual anchor for the Cognitive Memoisation (CM) corpus.

Cognitive Memoisation is a human-governed knowledge-engineering framework designed to preserve conceptual memory across interactions with stateless Large Language Models (LLMs). CM helps humans avoid repeated rediscovery (“Groundhog Day”) and carry forward both resolved knowledge and unresolved cognition (Dangling Cognates).

CM operates entirely outside model-internal memory, leveraging the power of LLMs to infer postulates and perform stochastic pattern matching, all under the curation of the human controlling the CM session.

The stateless nature of LLMs (such as ChatGPT) is an intentional design choice made for human safety and privacy. This design ensures that no personal or contextual information is retained across sessions, aligning with OpenAI's commitment to data protection. The safety mechanism prevents LLMs from making introspection or gaining agency, ensuring that the model does not evolve autonomously or retain knowledge beyond its interactions.

Cognitive Memoisation (CM) bridges this lack of memory by enabling humans to externalise cognitive artefacts, preserving knowledge over time. This allows for continuous human reasoning while keeping LLMs sand-boxed—both the human and the model are sandboxed to ensure security. Through CM, humans can elaborate on unresolved cognition (Dangling Cognates) and carry forward insights and propositions, while the LLM remains within its functional boundaries, executing only permitted tasks and with no capacity to alter its inherent state or memory.

This document establishes the rationale, scope, and interpretive framework required to understand Cognitive Memoisation and its role in enabling human-centric knowledge workflows with stateless LLMs.

Cognitive Memoisation Corpus Map

Canonical Dimension Table (Anchored)

Dim ID Canonical Dimension (verbatim) Scope Note
D1 Statelessness and Memory Management in LLMs LLM statelessness, safety, memory absence
D2 Externalisation of Cognitive Artefacts Durable external cognition
D3 Round-Trip Knowledge Engineering (RTKE) Re-ingestion, reuse, evolution
D4 Dangling Cognates and Unresolved Cognition Unfinished / provisional concepts
D5 Constraints and Knowledge Integrity Groundhog Day prevention
D6 Human Curated Knowledge vs. Model State Authority separation
D7 Reflexive Development of Cognitive Memoisation (RTKE Case Study) Self-referential development
D8 Dangling Cognates as First-Class Cognitive Constructs Formal DC elevation
D9 ChatGPT UI Boundary Friction as a Constraint on RTKE Platform limits
D10 Plain-Language Accessibility and Public Framing Reader-facing clarity
D11 Governance, Authority, and Failure Modes Control, breakdown, recovery
D12 Client-side Memoisation (CM-2) Mechanism disclosure

Time-Ordered Projection with Inline Dimensions

2025-12-17 — FOUNDATION

2025-12-18 — COMMUNICATION

2025-12-28 — PORTABILITY / SEMANTICS

2026-01-04 — MECHANISM / CORPUS ANCHOR

  • Cognitive Memoisation: Corpus Guide
    • D1 — Statelessness and Memory Management in LLMs
    • D2 — Externalisation of Cognitive Artefacts
    • D3 — Round-Trip Knowledge Engineering (RTKE)
    • D4 — Dangling Cognates and Unresolved Cognition
    • D5 — Constraints and Knowledge Integrity
    • D6 — Human Curated Knowledge vs. Model State
    • D7 — Reflexive Development of Cognitive Memoisation (RTKE Case Study)
    • D8 — Dangling Cognates as First-Class Cognitive Constructs
    • D9 — ChatGPT UI Boundary Friction as a Constraint on RTKE
    • D10 — Plain-Language Accessibility and Public Framing
    • D11 — Governance, Authority, and Failure Modes
    • D12 — Client-side Memoisation (CM-2)

2026-01-05 — GOVERNANCE, UI, SYSTEMS

2026-01-06 — FAILURE & RECOVERY

2026-01-08 — REFLEXIVE & GOVERNANCE THEORY

2026-01-10 to 2026-01-12 — SYNTHESIS & MYTH-BUSTING


Cognitive Memoisation: Corpus Mapping and Projection Invariants

Scope and Intent

This artefact enumerates the complete set of invariants required to:

  • construct the canonical dimension table
  • assign dimensions to corpus artefacts
  • produce time-ordered projections
  • produce divergence (dimension) projections
  • preserve epistemic discipline, provenance, and human authority

These invariants apply to corpus organisation and projection only. They do not introduce new CM definitions, modify CM-master invariants, or assert governance over reasoning behaviour.

Authority and Epistemic Position

  • All invariants herein are human-authored and curator-governed.
  • The assisting system MUST treat this artefact as binding for corpus mapping tasks when asserted.
  • These invariants govern representation and organisation, not truth, correctness, or inference.

Canonical Dimension Invariants

CM-CORPUS-INV-01 — Dimension Canonicality Invariant

Each dimension MUST have:

  • a stable identifier (e.g. D1, D2, …)
  • a single canonical name
  • a stable semantic scope

Dimension identifiers and names MUST NOT be inferred, renamed, merged, split, or reordered by the assisting system.

CM-CORPUS-INV-02 — Dimension Vocabulary Closure Invariant

The set of dimensions is closed.

No additional dimensions may be introduced unless explicitly declared by the human curator.

Absence of coverage MUST be represented as absence, not as invention.

CM-CORPUS-INV-03 — Dimension Semantic Fidelity Invariant

Assignment of a dimension to an artefact MUST reflect explicit scope alignment present in the artefact itself or in curator-supplied mapping.

The assisting system MUST NOT infer dimension relevance based on stylistic similarity, topic proximity, or semantic guesswork.

Artefact Identification Invariants

CM-CORPUS-INV-04 — Normative Title Fidelity Invariant

Artefacts MUST be referenced using their exact normative MediaWiki page titles.

Paraphrase, abbreviation, or normalisation of titles is prohibited.

CM-CORPUS-INV-05 — Artefact Identity Stability Invariant

An artefact is identified solely by its title and publication date.

Later editorial changes do not create new artefact identities unless explicitly versioned by the human.

Temporal Ordering Invariants

CM-CORPUS-INV-06 — Declared Date Authority Invariant

Time ordering MUST use the declared publication date as supplied by the human curator.

The assisting system MUST NOT infer, estimate, or correct dates.

If multiple dates exist, the curator MUST specify which date governs ordering.

CM-CORPUS-INV-07 — Sequence Over Precision Invariant

Temporal sequence is authoritative even if time precision is coarse.

Relative ordering MUST be preserved even when exact timestamps are unavailable.

Projection Construction Invariants

CM-CORPUS-INV-08 — Projection Non-Inference Invariant

Projections MUST NOT introduce:

  • new artefacts
  • new dimensions
  • new relationships
  • new interpretations

A projection is a re-expression of existing assignments only.

CM-CORPUS-INV-09 — Projection Completeness Invariant

Within declared scope, projections MUST include all eligible artefacts.

Selective omission constitutes a projection violation.

CM-CORPUS-INV-10 — Multi-Projection Consistency Invariant

All projections MUST be semantically consistent with one another.

Differences between projections may exist only in ordering or grouping, not in content.

Time-Ordered Projection Invariants

CM-CORPUS-INV-11 — Time-Ordered Projection Structure Invariant

A time-ordered projection MUST:

  • group artefacts by declared date
  • list artefacts within each group
  • attach dimensions as subordinate information

Time is the primary axis; dimensions are secondary.

CM-CORPUS-INV-12 — Inline Dimension Expansion Invariant

When dimensions are listed under artefacts:

  • each dimension MUST include both identifier and full canonical name
  • users MUST NOT be required to consult a separate table to understand dimension meaning

Divergence (Dimension) Projection Invariants

CM-CORPUS-INV-13 — Dimension-Centric Projection Structure Invariant

A divergence projection MUST:

  • use dimensions as the primary axis
  • list all artefacts participating in each dimension
  • preserve publication dates for temporal context

CM-CORPUS-INV-14 — Non-Exclusivity Invariant

Artefacts MAY appear under multiple dimensions.

Multiplicity is expected and MUST NOT be collapsed.

Representation and Emission Invariants

CM-CORPUS-INV-15 — MediaWiki-Only Emission Invariant

All corpus projections emitted as MWDUMP MUST use MediaWiki syntax exclusively.

Markdown, hybrid markup, or implicit formatting is prohibited.

CM-CORPUS-INV-16 — Bullet Level Semantics Invariant

Bullet depth conveys semantic hierarchy:

  • one asterisk (*) — artefact
    • two asterisks (**) — dimension assignment
      • three asterisks (***) — sub-dimension or note (if present)
        • four asterisks (****) — reserved

The assisting system MUST respect bullet depth semantics.

Human Readability and Governance Invariants

CM-CORPUS-INV-17 — Human Readability Invariant

Corpus projections MUST be intelligible to human readers without external tooling.

Abbreviation without expansion is prohibited.

CM-CORPUS-INV-18 — No Implied Authority Invariant

Presence of an artefact or dimension in a projection MUST NOT be interpreted as endorsement, priority, or correctness.

Organisation does not imply evaluation.

Change and Evolution Invariants

CM-CORPUS-INV-19 — Explicit Change Invariant

Any change to:

  • dimension set
  • dimension definitions
  • artefact–dimension assignments
  • projection rules

MUST be explicitly declared by the human curator.

Silent drift is prohibited.

CM-CORPUS-INV-20 — Backward Compatibility Invariant

Existing projections remain valid historical artefacts unless explicitly superseded.

New projections MUST NOT retroactively invalidate prior ones.

Summary for Human Readers

These invariants exist to ensure that the Cognitive Memoisation corpus:

  • remains navigable as it grows
  • can be read chronologically or thematically without confusion
  • preserves human authority over meaning and structure
  • avoids accidental reinterpretation by tooling or automation

They formalise how maps are drawn — not what the territory means.

Summary for Assisting Systems

When constructing corpus tables or projections:

  • do not invent
  • do not infer
  • do not optimise
  • do not rename
  • do not omit

Rearrange only what is already governed.

categories

Retrieved from ‘https://publications.arising.com.au:443/pub-dir/index.php?title=Cognitive_Memoisation:_corpus_guide&oldid=18368’