5.2 KiB
Model Dependency Map
1. Purpose
This file tracks relationships among models in the CCPE model library.
It answers:
Which models depend on which?
Which models derive from which?
Which models overlap?
Which models conflict?
Which models should be merged?
Which models have been deprecated or replaced?
This file is especially important when the library contains many models.
2. Relationship Types
Use these relationship types:
parent-model
child-model
prerequisite
derived-model
sibling-model
overlapping-model
conflicting-model
merged-into
supersedes
deprecated-by
supports
tensions-with
3. Mapping Format
Use this format for each model:
## {model-id}
### Parent Models
### Child Models / Derived Models
### Prerequisites
### Sibling Models
### Overlapping Models
### Conflicting Models
### Supports
### Tensions
### Notes
4. Initial Map
cognitive-imaging
Parent Models
Conceptual parent models:
prediction-error
free-energy-principle
algorithmic-compression
causal-intervention
complex-adaptive-systems
orthogonal-modeling
Status:
active model relationship; conceptual dependencies are not all standalone Model Cards yet
Child Models / Derived Models
Potential child or derived procedures:
prediction-error-capture
darkroom-suspension
multi-filter-enlarger
do-operator-test
conspiracy-breaker-check
cognitive-development-report
Status:
candidate procedures; most should become Skills only if Codex invocation or cross-agent reuse is needed
Prerequisites
Understanding of complex adaptive systems
Ability to distinguish correlation from causation
Awareness of model falsifiability
Tolerance for suspended judgment
Sibling Models
cognitive-prism
giant-cognition
Status:
candidate sibling relationship; needs user confirmation
Overlapping Models
systems-thinking
argument-compression
causal-analysis
Status:
external or candidate internal relationships
Conflicting Models
TBD
Supports
cognitive-imaging.skill.md
model-cards/intermediate/cognitive-imaging-model.md
agents/lite/cognitive-imaging-practitioner.prompt.md
article-review-committee.runtime.md (future candidate)
Tensions
Potential tensions:
May overuse hard-science filters.
May mistake anomaly detection for insight.
May over-privilege anti-intuitive conclusions.
Notes
Cognitive Imaging appears to function both as an intermediate model and as a workflow model.
It now has an active Model Card and an active CCPE-Lite prompt.
Skill, Agent Spec, and Runtime expansion is deferred until scenario demand is confirmed.
giant-cognition
Parent Models
TBD
Child Models / Derived Models
TBD
Prerequisites
TBD
Sibling Models
cognitive-imaging
cognitive-prism
Overlapping Models
TBD
Conflicting Models
TBD
Supports
model-cards/applied/giant-cognition-model.md
agents/lite/giant-cognition.prompt.md
review-committee.runtime.md (future candidate)
Tensions
May become too template-heavy if every review forces a full L0-L4 scan.
May over-emphasize cognitive architecture when a task only needs factual correction or light editing.
May confuse metaphorical model structure with empirical mechanism if used without boundary discipline.
Notes
Candidate applied model extracted from 《构建你自己的巨人 2.0》 and 巨人认知智能体2.2.
Current target form is Model Card + CCPE-Lite. Skill, Agent Spec, and Runtime conversion are deferred.
cognitive-prism
Parent Models
TBD
Child Models / Derived Models
TBD
Prerequisites
TBD
Sibling Models
cognitive-imaging
giant-cognition
Overlapping Models
TBD
Conflicting Models
TBD
Supports
TBD
Tensions
TBD
Notes
Candidate model. Requires source review and Model Mining.
5. Dependency Review Checklist
When adding or updating relationships, ask:
Is this a real dependency or just thematic similarity?
Does one model require the other?
Is one model a procedure derived from another?
Are these two models actually duplicates?
Is the relationship confirmed by source material?
Does the user need to confirm this relationship?
6. Candidate Relationship Policy
When uncertain, mark relationship as:
candidate relationship
Do not treat uncertain dependencies as canonical.
7. Merge Review Policy
Consider merge review when:
Two models share the same mechanism.
Two models differ only in name.
One model is a subroutine of another.
A candidate model is better represented as a Skill.
Do not merge when:
Two models share vocabulary but solve different problems.
Two models share metaphor but have different mechanisms.
One is a foundational model and the other is an applied model.
8. Final Rule
Dependency mapping should reveal the architecture of the user's thinking.
It should not create artificial order where the model relationships are still uncertain.