# ML Detection & Auto-Configuration

> Status: Active
> Audience: Team, AI agents, curious developers
> Purpose: Portal into the ML detection knowledge base

This section explains how Niamoto detects semantic column types, how the ML
stack is trained and evaluated, and where to find the current research,
experiments, and dated planning material.

## Start here

- **[Overview](overview.md)**: what the system does, why it exists, current
  scores, and the main limits.
- **[Branch Architecture](branch-architecture.md)**: the hybrid pipeline,
  product priorities, and the role of autoresearch.
- **[Training & Evaluation Guide](training-guide.md)**: the reproducible
  workflow from `ml/data/silver` to trained models and evaluation results.

## If you want to...

- **Understand the implementation**
  - [Overview](overview.md)
  - [Branch Architecture](branch-architecture.md)
  - [Current Training Sources](current-training-sources.md)
- **Train or evaluate the stack**
  - [Training & Evaluation Guide](training-guide.md)
  - `ml/README.md`
- **Understand current autoresearch rules**
  - [Autoresearch Surrogate Loop](autoresearch-surrogate-loop.md)
  - `ml/programmes/`
- **Review experiment history**
  - [Experiments index](experiments/README.md)
- **Review exploratory ideas or older planning docs**
  - [Research notes](research/README.md)
  - [Archive](archive/README.md)
- **Find the latest dated plans**
  - `docs/plans/`

## Structure

### Active reference

- [Overview](overview.md)
- [Branch Architecture](branch-architecture.md)
- [Training & Evaluation Guide](training-guide.md)
- [Current Training Sources](current-training-sources.md)
- [Autoresearch Surrogate Loop](autoresearch-surrogate-loop.md)
- [ML Detection Dashboard](ml-detection-dashboard.html)

### Research

- [Research notes index](research/README.md)

### Experiments

- [Experiments index](experiments/README.md)

### Archive

- [Archive index](archive/README.md)

## Related runtime and code-adjacent docs

- `ml/README.md` — operational commands and where to look in the offline ML
  workspace
- [User Guide](../02-user-guide/README.md) — how ML auto-detection
  plugs into the import workflow
- [Reference](../06-reference/README.md) — API-level documentation and
  config schemas

```{toctree}
:hidden:

overview
branch-architecture
training-guide
current-training-sources
autoresearch-surrogate-loop
research/README
experiments/README
archive/README
```