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

Extraction Log

1. Purpose

This file records model extraction events.

Use it to track how models are extracted from articles, prompts, discussions, notes, and other source material.

The extraction log helps preserve provenance.

It answers:

Where did this model come from?
When was it extracted?
What confidence level was assigned?
What needs user review?
What was promoted, rejected, merged, or deferred?

2. Entry Format

Use this format for each extraction event:

## YYYY-MM-DD — {Source Title}

### Source

```text
title:
path:
author:
source_type:
date_written:

Extraction Context

reason_for_extraction:
requested_by:
extractor:
mode: Model Mining Mode

Extracted Models

Model ID	Model Name	Type	Confidence	Status	Proposed Path	Notes

Non-Model Ideas

-
-
-

Skill Conversion Candidates

-
-
-

Agent Conversion Candidates

-
-
-

Runtime Usage Candidates

-
-
-

Open Questions

1.
2.
3.

Next Action

3. Confidence Levels

Use:

high
medium
low

high

The model is explicit, named, and structurally complete.

medium

The model is strongly implied but not fully formalized.

low

The model is plausible but requires user confirmation.

4. Status Values

Use:

candidate
draft
active
rejected
merged
deprecated
archived

Default for implicit extractions:

candidate

Default for structurally clear but unconfirmed extractions:

draft

Use active only after user confirmation.

5. Initial Extraction Notes

2026-05-31 — Initial Known Model Seed

Source

title: User-provided examples in CCPE System construction discussion
path: conversation context
author: Wantsong
source_type: discussion
date_written: 2026-05-31

Extraction Context

reason_for_extraction: Initialize model library with known model names mentioned by user.
requested_by: Wantsong
extractor: CCPE Forge planning process
mode: Model Mining Mode

Extracted Models

Model ID	Model Name	Type	Confidence	Status	Proposed Path	Notes
cognitive-imaging	认知显影 / Cognitive Imaging	intermediate; workflow-model	high	active	model-cards/intermediate/cognitive-imaging-model.md	Promoted after source review, Lite regression tests, and user confirmation.
giant-cognition	巨人认知 / Giant Cognition	applied	high	candidate	model-cards/applied/giant-cognition-model.md	Source material provided and Model Card created on 2026-06-01.
cognitive-prism	认知棱镜 / Cognitive Prism	intermediate; applied	medium	candidate	TBD	Mentioned as an existing review model. Source material needed.

Non-Model Ideas

- CCPE Forge as Creator / Auditor / Refactor / Model Mining Skill
- Review Committee as possible Hybrid Runtime
- Human-in-the-loop as design principle

Skill Conversion Candidates

- cognitive-imaging.skill.md
- prediction-error-capture.skill.md
- do-operator-test.skill.md
- model-mining.skill.md

Agent Conversion Candidates

- cognitive-imaging-practitioner.agent.md (deferred)
- review-committee-chair.agent.md

Runtime Usage Candidates

- review-committee.runtime.md
- modeling-committee.runtime.md
- article-to-model-extraction.runtime.md

Open Questions

1. Should Cognitive Imaging be marked active after full Model Card creation?
2. Should Cognitive Prism be extracted from source articles before indexing further?
3. Should prediction-error-capture be a separate Model Card or only a Skill under Cognitive Imaging?

Next Action

Create full Model Card for Cognitive Imaging from source material.
Then run Model Mining Mode on source articles for Cognitive Prism.

2026-06-01 — 认知显影 Model Card Promotion

Source

title: 大脑暗房：关于洞察力的显影术; 认知显影者1.1
path: workbench/raw/2026-01-06-the-darkroom-of-brain.md; workbench/raw/认知显影者1.1.md
author: Wantsong
source_type: article; legacy agent prompt
date_written: 2026-01-06; unknown

Extraction Context

reason_for_extraction: Promote the stable embedded cognitive model behind 认知显影者 Lite into a canonical Model Card and update the active Model Index.
requested_by: Wantsong
extractor: CCPE Forge
mode: Model Mining Mode

Extracted Models

Model ID	Model Name	Type	Confidence	Status	Proposed Path	Notes
cognitive-imaging	认知显影 / Cognitive Imaging	intermediate; workflow-model	high	active	model-cards/intermediate/cognitive-imaging-model.md	Stable named model. Active Lite prompt exists at agents/lite/cognitive-imaging-practitioner.prompt.md.

Non-Model Ideas

- 认知显影 as a Web-style expert prompt.
- Article review committee as a future orchestration pattern.
- Scenario probe as a CCPE classification prerequisite.

Skill Conversion Candidates

- cognitive-imaging.skill.md
- prediction-error-capture.skill.md
- causal-exposure-test.skill.md

Skill conversion is deferred. It should happen only if Codex automatic invocation or cross-agent method reuse becomes necessary.

Agent Conversion Candidates

- cognitive-imaging-practitioner.agent.md

Agent conversion is deferred. The active production artifact is currently the Lite prompt.

Runtime Usage Candidates

- article-review-committee.runtime.md
- modeling-committee.runtime.md

Runtime design is deferred until the other review or modeling agents are upgraded.

Open Questions

1. Should prediction-error-capture become a separate Skill later?
2. Should causal-exposure-test be generalized as a reusable evaluation Skill?
3. Which future committee should first consume 认知显影 as a formal Agent node?

Next Action

Keep 认知显影 active as Model Card + Lite Prompt.
Do not create Skill, Agent Spec, or Runtime until scenario demand appears.

2026-06-01 — 巨人认知 Model Card Creation

Source

title: 构建你自己的巨人 2.0; 巨人认知智能体2.2
path: user-provided pasted text; agents/lite/giant-cognition.prompt.md
author: Wantsong
source_type: article; legacy agent prompt
date_written: 2025-11-27; 2026-03-06

Extraction Context

reason_for_extraction: Refactor the existing 巨人认知智能体 into a portable Lite prompt and a single Model Card for the application-oriented cognitive review model.
requested_by: Wantsong
extractor: CCPE Forge
mode: Refactor Mode + Model Mining Mode

Extracted Models

Model ID	Model Name	Type	Confidence	Status	Proposed Path	Notes
giant-cognition	巨人认知 / Giant Cognition	applied	high	candidate	model-cards/applied/giant-cognition-model.md	User confirmed the model should remain a single Model Card. 双循环罗盘 and 五层甲板 are internal mechanisms, not separate Model Cards.

Non-Model Ideas

- 巨人认知 as a Web-style expert review prompt.
- 双循环罗盘 as the internal dynamic mechanism of 巨人认知.
- 五层甲板 as the internal layered diagnostic structure of 巨人认知.
- 思想考古学家 as a GL3-oriented review stance inside the model.

Skill Conversion Candidates

- giant-cognition-review.skill.md (deferred)

Skill conversion is deferred. It should happen only if Codex automatic invocation or cross-agent method reuse becomes necessary.

Agent Conversion Candidates

- giant-cognition.agent.md (deferred)

Agent conversion is deferred. The current production artifact is the Lite prompt.

Runtime Usage Candidates

- review-committee.runtime.md

Runtime design is deferred until multiple review agents are upgraded and their collaboration contracts are clear.

Open Questions

1. Should 巨人认知 become active after user review of the Lite prompt and Model Card?
2. Should future review committee design treat 巨人认知 as one committee member or as a shared review model?
3. Should 《构建你自己的巨人 2.0》 later yield a broader foundational model, separate from this applied review model?

Next Action

Review generated files:
- agents/lite/giant-cognition.prompt.md
- model-cards/applied/giant-cognition-model.md

If approved, promote giant-cognition from candidate to active.

6. Maintenance Rules

When a new extraction is performed:

1. Add an entry with date and source.
2. Record all extracted models.
3. Record confidence level.
4. Record status.
5. Record proposed Model Card path.
6. Record Skill / Agent / Runtime conversion candidates.
7. Record open questions.
8. Update model-index.md.
9. Update model-dependency-map.md if relationships are known.
10. Update model-usage-map.md if usage is known.

7. Final Rule

The extraction log should make model formation traceable.

A model without provenance is harder to trust, harder to revise, and harder to integrate.