---
configs:
- config_name: default
  data_files:
  - split: train
    path: data/*.jsonl
---

# SLM Synthetic DPO — basic_arithmetic_qa

## Summary

Synthetic preference-pair dataset containing chosen and rejected assistant responses for `basic_arithmetic_qa`.

## Dataset

- Dataset type: `preference optimization`
- Total pairs: `6429`
- Signal: `basic_arithmetic_qa`
- Language: English

## Signal Metadata

- Category: `direct_arithmetic`
- Difficulty: `1`
- Template family: `direct_addition`
- Eval family: `basic_arithmetic_qa`

## Schema

```json
{
  "id": "string",
  "prompt": [
    {"role": "user", "content": "string"}
  ],
  "chosen": [
    {"role": "assistant", "content": "string"}
  ],
  "rejected": [
    {"role": "assistant", "content": "string"}
  ],
  "metadata": {
    "category": "string",
    "difficulty": 1,
    "template_family": "string",
    "eval_family": "string",
    "failure_mode": "string"
  }
}
```

## Intended Use

Use this dataset for DPO-style preference optimization experiments targeting this signal.

## Limitations

This dataset is synthetic and encodes targeted preference behavior. Inspect chosen/rejected pairs before training.