{"kind":"task","effective_mode":"full","benchmark":{"kind":"benchmark","effective_mode":"full","slug":"bigcodebench","formal_name":"BigCodeBench","introduction":"BigCodeBench poses 1,140 function-level tasks drawn across 139 libraries. It tests whether a model can compose several real APIs correctly rather than write one self-contained function.","introduction_ja":"","introduction_en":"","category":"Category not supplied","task_count":null,"acquisition_status":"Acquisition status not supplied","official_url":"https://bigcode-bench.github.io/","indexing_mode":"index","profile":{"resources":[],"task_format":"","scoring":"","metric":"","size":"","answer_access":"","license":"","citation":"","maintainer":"","released":"","why_hard":"","related":[],"history":"","construction":"","limitations":"","saturation":"","scores":[]}},"task_id":"40d69964-00cd-5f7c-8c8b-7089fd733b34","task_key":"default--v0~2e1~2e0~5fhf--40d69964-00cd-5f7c-8c8b-7089fd733b34","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 40d69964-00cd-5f7c-8c8b-7089fd733b34","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import json\\nimport base64\\nimport unicodedata\\ndef task_func(json_file: str) -> dict:\\n\",\"complete_prompt\":\"import json\\nimport base64\\nimport unicodedata\\n\\ndef task_func(json_file: str) -> dict:\\n    \\\"\\\"\\\"\\n    This function reads a JSON file where each key is a unique identifier, and the corresponding value is a base64 encoded string.\\n    After decoding, it applies Unicode normalization form C (NFC) to each decoded string to ensure the canonical composition of characters.\\n    The function returns a dictionary where the keys are preserved, and the values are the normalized, decoded strings. Decoding is performed using the UTF-8 encoding scheme.\\n\\n    Parameters:\\n    - json_file (str): The path to the JSON file.\\n\\n    Returns:\\n    - dict: A dictionary where each key is mapped to a normalized, decoded string from the base64 encoded value in the input file.\\n\\n    Requirements:\\n    - unicodedata\\n    - json\\n    - base64\\n\\n    Examples:\\n    Given a file 'example.json' with the content:\\n    {\\\"key1\\\": \\\"SGVsbG8gV29ybGQ=\\\", \\\"key2\\\": \\\"UHl0aG9uIENvZGUgUmVmaW5lcg==\\\"}\\n\\n    >>> task_func('example.json')\\n    {'key1': 'Hello World', 'key2': 'Python Code Refiner'}\\n\\n    Given a file 'empty.json' with the content:\\n    {}\\n\\n    >>> task_func('empty.json')\\n    {}\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"This function reads a JSON file where each key is a unique identifier, and the corresponding value is a base64 encoded string. After decoding, it applies Unicode normalization form C (NFC) to each decoded string to ensure the canonical composition of characters. The function returns a dictionary where the keys are preserved, and the values are the normalized, decoded strings. Decoding is performed using the UTF-8 encoding scheme. >>> task_func('example.json') {'key1': 'Hello World', 'key2': 'Python Code Refiner'} Given a file 'empty.json' with the content: {} >>> task_func('empty.json') {}\\nThe function should output with:\\n    dict: A dictionary where each key is mapped to a normalized, decoded string from the base64 encoded value in the input file.\\nYou should write self-contained code starting with:\\n```\\nimport json\\nimport base64\\nimport unicodedata\\ndef task_func(json_file: str) -> dict:\\n```\",\"libs\":\"['base64', 'unicodedata', 'json']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}