Neural architectures for resolving references in program code

2026-04-15

AI Summary

This work addresses the challenges of resolving direct and indirect code references in decompilation by formalizing reference rewriting as a permutation-based indexing task. The authors construct the first synthetic benchmark for this problem and introduce a novel sequence-to-sequence neural architecture that integrates permutation modeling with a dedicated indexing mechanism. The proposed model significantly outperforms existing approaches in both robustness and scalability: it handles input sequences ten times longer than those processed by the strongest baseline and reduces error rates by 42% on decompiling switch statements. Ablation studies confirm the necessity of each architectural component.

Technology Category

Natural Language Processing: Code Generation / Program Synthesis from Natural LanguageMachine Learning: Deep Neural Architectures and Foundation ModelsCognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphsUser Modeling, Personalization and Recommendation: Fairness-aware retrieval and rankingSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Resolving and rewriting references is fundamental in programming languages. Motivated by a real-world decompilation task, we abstract reference rewriting into the problems of direct and indirect indexing by permutation. We create synthetic benchmarks for these tasks and show that well-known sequence-to-sequence machine learning architectures are struggling on these benchmarks. We introduce new sequence-to-sequence architectures for both problems. Our measurements show that our architectures outperform the baselines in both robustness and scalability: our models can handle examples that are ten times longer compared to the best baseline. We measure the impact of our architecture in the real-world task of decompiling switch statements, which has an indexing subtask. According to our measurements, the extended model decreases the error rate by 42%. Multiple ablation studies show that all components of our architectures are essential.

Problem

• reference resolution
• decompilation
• indexing
• program code
• switch statements

Innovation

• reference resolution
• sequence-to-sequence architecture
• permutation-based indexing
• decompilation
• synthetic benchmark