ccpe-system/model-index/model-taxonomy.md

314 lines
6.2 KiB
Markdown

# Model Taxonomy
## 1. Purpose
This file defines the taxonomy used to organize the CCPE model library.
The taxonomy is not meant to be rigid.
It is a working classification system for managing many cognitive models extracted from articles, prompts, agents, and discussions.
## 2. Primary Taxonomy
The model library uses the following top-level categories:
```text
1. Foundational Models
2. Intermediate Models
3. Applied Models
4. Workflow Models
5. Implicit Extracted Models
6. Deprecated / Archived Models
```
## 3. Foundational Models
### 3.1 Definition
Foundational Models define deep assumptions, primitives, or explanatory structures that support many other models.
They often operate at the level of:
```text
Cognition
Causality
Complex systems
Information compression
Entropy / anti-entropy
Agency
Learning
Model formation
```
### 3.2 Typical Signs
A model is foundational when:
```text
Many other models depend on it.
It defines basic assumptions.
It appears repeatedly across articles.
It is not tied to one narrow application.
It influences how other models are interpreted.
```
### 3.3 Examples
```text
TBD
```
Possible future candidates:
```text
Prediction Error Model
Algorithmic Compression Model
Complex Adaptive Systems Assumption
Causal Intervention Principle
Anti-Entropy Insight Principle
```
## 4. Intermediate Models
### 4.1 Definition
Intermediate Models organize a domain, thinking pattern, or reasoning method.
They are more concrete than foundational models but broader than applied models.
### 4.2 Typical Signs
A model is intermediate when:
```text
It has a named framework.
It has a coherent mechanism.
It can be applied to multiple situations.
It may produce multiple Skills.
It can be used by several Agents.
```
### 4.3 Initial Examples
```text
认知显影 / Cognitive Imaging
巨人认知 / Giant Cognition
认知棱镜 / Cognitive Prism
```
## 5. Applied Models
### 5.1 Definition
Applied Models are designed for a specific task, domain, or practical use case.
They usually depend on foundational or intermediate models.
### 5.2 Typical Signs
A model is applied when:
```text
It solves a specific operational problem.
It has narrow usage boundaries.
It can directly guide an Agent or Skill.
It may be derived from a broader model.
```
### 5.3 Examples
```text
Article Critique Model
Strategic Risk Review Model
Concept Boundary Inspection Model
Argument Repair Model
```
## 6. Workflow Models
### 6.1 Definition
Workflow Models naturally become repeatable procedures.
They are often convertible into CCPE-Skills or CCPE-Runtimes.
### 6.2 Typical Signs
A model is workflow-oriented when:
```text
It has steps or phases.
It defines a repeatable process.
It produces a stable output.
It has trigger conditions.
It can be validated.
```
### 6.3 Examples
```text
Cognitive Imaging Five-Step Procedure
Model Mining Pipeline
Review Committee Workflow
Article-to-Model Extraction Process
```
## 7. Implicit Extracted Models
### 7.1 Definition
Implicit Extracted Models are reconstructed from writing or discussion where the author did not explicitly frame the idea as a model.
### 7.2 Typical Signs
A model is implicit when:
```text
The same explanatory logic appears repeatedly.
A stable metaphor carries mechanism.
A hidden taxonomy appears across arguments.
A repeated causal pattern is visible.
The model can be named only after extraction.
```
### 7.3 Handling Rules
Implicit models should normally start as:
```text
candidate
```
They require user confirmation before becoming active.
## 8. Deprecated / Archived Models
### 8.1 Definition
Deprecated or archived models are preserved for history but are not currently recommended as active components.
### 8.2 Reasons for Deprecation
```text
Superseded by a better model.
Merged into another model.
Extracted incorrectly.
Rejected by user.
No longer represents current thinking.
Too vague to use.
```
## 9. Secondary Tags
In addition to primary taxonomy, use secondary tags when helpful.
### 9.1 Domain Tags
```text
cognition
writing
argumentation
strategy
complex-systems
agent-design
knowledge-management
evaluation
coding
organization
```
### 9.2 Function Tags
```text
diagnostic
generative
evaluative
compressive
causal
synthetic
critical
archival
transformative
```
### 9.3 Usage Tags
```text
agent-ready
skill-ready
runtime-ready
model-card-needed
needs-review
```
## 10. Layer System
Use the layer system to locate models structurally.
```text
L0: Foundational Assumption
L1: Foundational Model
L2: Intermediate Model
L3: Applied Model
L4: Workflow / Procedure Model
L5: Output / Evaluation Lens
```
## 11. Multi-Layer Models
Some models may belong to more than one layer.
Example:
```text
Cognitive Imaging
= L2 Intermediate Model
+ L4 Workflow / Procedure Model
```
This is acceptable.
Do not force a model into one layer if it genuinely spans levels.
## 12. Taxonomy Maintenance Rules
When adding a new model:
```text
1. Assign primary taxonomy.
2. Assign layer.
3. Add secondary tags if useful.
4. Record uncertainty.
5. Update Model Index.
6. Update dependency map if relationships are known.
7. Update usage map if used by Agents or Skills.
```
## 13. Taxonomy Review Questions
Ask:
```text
Is this model foundational or applied?
Is it a model or a Skill?
Is it a model or a metaphor?
Does it depend on another model?
Is it actually a sub-model of an existing one?
Should it be merged?
Should it remain candidate?
```
## 14. Initial Taxonomy Placement
| Model ID | Model Name | Primary Category | Layer | Notes |
| ----------------- | ------------------------- | ---------------------- | ------ | ---------------------------- |
| cognitive-imaging | 认知显影 / Cognitive Imaging | Intermediate; Workflow; Evaluation Lens | L2; L4; L5 | Active Model Card; active Lite prompt |
| giant-cognition | 巨人认知 / Giant Cognition | Intermediate | L2 | Candidate |
| cognitive-prism | 认知棱镜 / Cognitive Prism | Intermediate; Applied | L2; L3 | Candidate |
## 15. Final Rule
The taxonomy should help navigation, not imprison thinking.
If a model resists the taxonomy, record the tension instead of forcing a false category.