Research map / Large language models / Agents, code and math
Disjunctive Program Synthesis: A Robust Approach to Programming by Example
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| synthesize disjunctive programs with execution-time selection instead of a single ranked program (ablation) | PBE text and web extraction (PROSE DSLs) · Email extraction benchmarks (47 tasks) | % tasks correct from one example: 59.6% -> 93.6% | Helped |
| use disjunctive programs (multiple branches evaluated at execution) (ablation) | PBE extraction programs · Email extraction benchmarks | execution time: 2.9x slowdown | Hurt |
Closest papers by meaning
- Is Programming by Example Solved by LLMs? (NeurIPS 2024 · similarity 0.90)
- Grammar Filtering for Syntax-Guided Synthesis (AAAI 2020 · similarity 0.89)
- Program Synthesis via Test-Time Transduction (NeurIPS 2025 · similarity 0.85)
- BaxBench: Can LLMs Generate Correct and Secure Backends? (ICML 2025 · similarity 0.84)
- Synthetic Programming Elicitation for Text-to-Code in Very Low-Resource Programming and Formal Languages (NeurIPS 2024 · similarity 0.84)
- Training Language Models on Synthetic Edit Sequences Improves Code Synthesis (ICLR 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.