# Baseline Before Content Stabilization v0.2

Date: 2026-06-16

## Scope

This baseline was captured before the v0.2 content stabilization pass for:

- `qpi`
- `intellectual_archaeology`

No third model is in scope.

## Baseline Commands

```powershell
python -m unittest discover -s tests -p "test*.py" -v
python scripts\check_card_contract.py
python scripts\validate_model_library.py
python scripts\run_selector_demo.py
python scripts\rebuild_indexes.py --check
```

## Results

- Unit tests: PASS, 14 tests.
- Card contract: PASS.
- Model library validation: PASS.
- Selector demo: PASS.
- Model/card index check: PASS.

## Current Asset Counts

- Models: 2
- Source articles: 3
- Source evidence excerpts: 10
- Regression cases: 10 total, 5 per model
- Selector examples: 3

## Current Model State

| Model ID | Status | Stability | Regression Status |
| --- | --- | --- | --- |
| `qpi` | draft | B | pending |
| `intellectual_archaeology` | draft | B | pending |

## What PASS Means

PASS means:

- JSON files are parseable.
- Required contract fields exist.
- Source article and source excerpt references resolve.
- Regression cases reference known models.
- Model/card indexes are synchronized.
- Markdown cards contain required headings.

## What PASS Does Not Mean

PASS does not mean:

- Model content is stable.
- Evidence is sufficient at field level.
- Raw excerpts are all exact quotes.
- Regression cases are strong enough for stable use.
- Selector behavior is protected against false positive recall.
- QPI or Intellectual Archaeology can be upgraded to stable.