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

175 lines
4.9 KiB
Markdown

# Model Index
## 1. Purpose
This file is the main index of the CCPE model library.
It records all known cognitive models, candidate models, extracted models, deprecated models, and model assets used by Agents, Skills, and Runtimes.
The Model Index is the map.
The Model Card is the full model record.
## 2. Status Legend
Use these status values:
```text
candidate
draft
active
rejected
merged
deprecated
archived
```
### candidate
A possible model has been identified but still needs review.
### draft
The model structure is clear enough to document, but not yet confirmed as canonical.
### active
The user has confirmed the model as part of the active model library.
### rejected
The candidate was reviewed and rejected as a model.
### merged
The model was merged into another model.
### deprecated
The model is preserved historically but no longer recommended.
### archived
The model is inactive and kept only for historical reference.
## 3. Review Status Legend
Use these review status values:
```text
needs-source-check
needs-user-confirmation
needs-scope-review
needs-falsification-boundary
needs-merge-review
reviewed
```
## 4. Model Type Legend
Use one or more:
```text
foundational
intermediate
applied
workflow-model
implicit-extracted
candidate
deprecated
```
## 5. Layer Legend
Use one or more:
```text
L0: Foundational Assumption
L1: Foundational Model
L2: Intermediate Model
L3: Applied Model
L4: Workflow / Procedure Model
L5: Output / Evaluation Lens
```
## 6. Main Model Index
| Model ID | Model Name | Type | Layer | Status | Canonical Path | Source | Related Agents | Related Skills | Review Status |
| ----------------- | ------------------------- | ---------------------------- | ------ | --------- | --------------------------------------------------- | ------ | ---------------------------- | ----------------- | ----------------------- |
| cognitive-imaging | 认知显影 / Cognitive Imaging | intermediate; workflow-model | L2; L4; L5 | active | model-cards/intermediate/cognitive-imaging-model.md | workbench/raw/2026-01-06-the-darkroom-of-brain.md; workbench/raw/认知显影者1.1.md | cognitive-imaging-practitioner-lite | TBD | reviewed |
| giant-cognition | 巨人认知 / Giant Cognition | applied | L3 | candidate | model-cards/applied/giant-cognition-model.md | 《构建你自己的巨人 2.0》; 巨人认知智能体2.2 | giant-cognition | TBD | needs-user-confirmation |
| cognitive-prism | 认知棱镜 / Cognitive Prism | intermediate; applied | L2; L3 | candidate | TBD | TBD | TBD | TBD | needs-source-check |
## 7. Candidate Models
Use this section for models identified but not yet ready for full Model Cards.
| Candidate ID | Provisional Name | Source | Confidence | Reason for Candidate Status | Next Action |
| ------------ | ---------------- | ------ | ---------- | --------------------------- | ----------- |
| TBD | TBD | TBD | TBD | TBD | TBD |
## 8. Active Models
Move confirmed active models here after user approval.
| Model ID | Model Name | Canonical Path | Primary Usage | Notes |
| -------- | ---------- | -------------- | ------------- | ----- |
| cognitive-imaging | 认知显影 / Cognitive Imaging | model-cards/intermediate/cognitive-imaging-model.md | Web-style expert review; article critique; cognitive model pressure testing | Active Lite: agents/lite/cognitive-imaging-practitioner.prompt.md |
## 9. Deprecated / Merged Models
| Model ID | Model Name | Status | Successor / Merge Target | Reason | Notes |
| -------- | ---------- | ------ | ------------------------ | ------ | ----- |
| TBD | TBD | TBD | TBD | TBD | TBD |
## 10. Maintenance Rules
When adding a model:
```text
1. Assign a stable model_id.
2. Add model name and aliases.
3. Mark type and layer.
4. Set status.
5. Link canonical path if Model Card exists.
6. Record source.
7. Record related agents and skills if known.
8. Add review status.
9. Update dependency map if relationships are known.
10. Update usage map if used by Agents, Skills, or Runtimes.
```
## 11. Promotion Rules
Candidate → Draft when:
```text
Model structure is clear.
Source is identified.
Scope and mechanism are present.
```
Draft → Active when:
```text
User confirms model name.
User confirms scope.
Model Card exists.
Falsification boundary exists.
Usage map is updated.
```
Active → Deprecated when:
```text
User rejects it.
It is superseded.
It merges into another model.
It no longer represents current thinking.
```
## 12. Notes
The initial entries are placeholders based on known user model names.
They should be reviewed through Model Mining Mode before being promoted to active status.