"""SimpleQA (OpenAI; official release is the CSV in github.com/openai/simple-evals).

The HF id below is the standard community mirror of that CSV.
"""

from ..sample import Sample
from ..registry import register_dataset
from ..spec import DatasetSpec


@register_dataset(
    DatasetSpec(
        name='simple_qa',
        source='basicv8vc/SimpleQA',  # mirror of the official openai/simple-evals CSV
        split='test',
        prompt_style='simple_qa_es',  # es: 'Answer the question:' header, NO answer-line contract
        task_type='qa',
        tags=['factuality'],
        description='SimpleQA factuality benchmark (OpenAI, community mirror of official CSV).',
    )
)
def simple_qa():
    def to_sample(record: dict) -> Sample:
        return Sample(
            input=record['problem'],
            target=str(record['answer']).strip(),
            metadata={'metadata': record.get('metadata')},
        )

    return to_sample