"""LiveCodeBench code generation lite (official source: livecodebench/code_generation_lite).""" from ..sample import Sample from ..registry import register_dataset from ..spec import DatasetSpec @register_dataset( DatasetSpec( name='live_code_bench', source='sam-paech/livecodebench-code_generation_lite', # HF parquet conversion; the official # livecodebench/code_generation_lite is script-based (unloadable by datasets>=5) subset='release_latest', # or release_v1..v6 split='test', task_type='coding', tags=['code'], description='LiveCodeBench (lite) contest problems; version tags via DatasetSpec.version.', params={'hub': 'hf_raw'}, ) ) def live_code_bench(): def to_sample(record: dict) -> Sample: return Sample( input=record['question_content'], target='', # judged by running hidden test cases, no reference text metadata={ 'question_id': record['question_id'], 'contest_id': record.get('contest_id'), 'contest_date': record.get('contest_date'), 'platform': record.get('platform'), 'difficulty': record.get('difficulty'), 'starter_code': record.get('starter_code'), 'public_test_cases': record.get('public_test_cases'), 'private_test_cases': record.get('private_test_cases'), }, ) return to_sample