Dataset Groups Activity Stream Search-based Pseudocode to Code The SPoC dataset contains 18,356 C++ programs with human-authored pseudocode and test cases. BibTex: @dataset{Sumith_Kulal_and_Panupong_Pasupat_and_Kartik_Chandra_and_Mina_Lee_and_Oded_Padon_and_Alex_Aiken_and_Percy_Liang_2024, abstract = {The SPoC dataset contains 18,356 C++ programs with human-authored pseudocode and test cases.}, author = {Sumith Kulal and Panupong Pasupat and Kartik Chandra and Mina Lee and Oded Padon and Alex Aiken and Percy Liang}, doi = {10.57702/3o3139xx}, institution = {No Organization}, keyword = {'natural language to code', 'program synthesis', 'pseudocode', 'test cases'}, month = {dec}, publisher = {TIB}, title = {Search-based Pseudocode to Code}, url = {https://service.tib.eu/ldmservice/dataset/search-based-pseudocode-to-code}, year = {2024} }
