Saved in:
Bibliographic Details
Main Authors: Szalay, Gergő, Kovács, Gergely Zsolt, Teleki, Sándor, Pintér, Balázs, Gregorics, Tibor
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.14073
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908966959710208
author Szalay, Gergő
Kovács, Gergely Zsolt
Teleki, Sándor
Pintér, Balázs
Gregorics, Tibor
author_facet Szalay, Gergő
Kovács, Gergely Zsolt
Teleki, Sándor
Pintér, Balázs
Gregorics, Tibor
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_14073
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Neural architectures for resolving references in program code
Szalay, Gergő
Kovács, Gergely Zsolt
Teleki, Sándor
Pintér, Balázs
Gregorics, Tibor
Machine Learning
Neural and Evolutionary Computing
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.
title Neural architectures for resolving references in program code
topic Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2604.14073