# Semantic Scaffolds for Pseudocode-to-Code Generation

arXiv: https://arxiv.org/abs/2005.05927 · HTML: https://mlsanity.com/paper/2005.05927/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 May 2020.

## Built on by (most cited first, 5 of 5)

- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [Towards Top-Down Automated Development in Limited Scopes: A Neuro-Symbolic Framework from Expressibles to Executables](https://mlsanity.com/paper/2209.01566/) (2022)
- [Knowledge Transfer for Pseudo-code Generation from Low Resource Programming Language](https://mlsanity.com/paper/2303.09062/) (2023)
- [Scaling Automatic Extraction of Pseudocode](https://mlsanity.com/paper/2406.04635/) (2024)
- [DuET: Dual Execution for Test Output Prediction with Generated Code and Pseudocode](https://mlsanity.com/paper/2604.11514/) (2026)

## Abstract (arXiv)

We propose a method for program generation based on semantic scaffolds, lightweight structures representing the high-level semantic and syntactic composition of a program. By first searching over plausible scaffolds then using these as constraints for a beam search over programs, we achieve better coverage of the search space when compared with existing techniques. We apply our hierarchical search method to the SPoC dataset for pseudocode-to-code generation, in which we are given line-level natural language pseudocode annotations and aim to produce a program satisfying execution-based test cases. By using semantic scaffolds during inference, we achieve a 10% absolute improvement in top-100 accuracy over the previous state-of-the-art. Additionally, we require only 11 candidates to reach the top-3000 performance of the previous best approach when tested against unseen problems, demonstrating a substantial improvement in efficiency.