# Embedding Software Intent: Lightweight Java Module Recovery

arXiv: https://arxiv.org/abs/2512.15980 · HTML: https://mlsanity.com/paper/2512.15980/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 90 references that are in the map.
- First posted on arXiv 17 Dec 2025.

## Builds on (most cited first, 11 of 11)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [CodeT5+: Open Code Large Language Models for Code Understanding and Generation](https://mlsanity.com/paper/2305.07922/) (2023)
- [On the Explainability of Natural Language Processing Deep Models](https://mlsanity.com/paper/2210.06929/) (2022)
- [Software Architecture Recovery with Information Fusion](https://mlsanity.com/paper/2311.04643/) (2023)
- [Software Architecture in Practice: Challenges and Opportunities](https://mlsanity.com/paper/2308.09978/) (2023)
- [Relationships between Software Architecture and Source Code in Practice: An Exploratory Survey and Interview](https://mlsanity.com/paper/2108.01018/) (2021)
- [Semantic Slicing of Architectural Change Commits: Towards Semantic Design Review](https://mlsanity.com/paper/2109.00659/) (2021)

## Abstract (arXiv)

As an increasing number of software systems reach unprecedented scale, relying solely on code-level abstractions is becoming impractical. While architectural abstractions offer a means to manage these systems, maintaining their consistency with the actual code has been problematic. The Java Platform Module System (JPMS), introduced in Java 9, addresses this limitation by enabling explicit module specification at the language level. JPMS enhances architectural implementation through improved encapsulation and direct specification of ground-truth architectures within Java projects. Although many projects are written in Java, modularizing existing monolithic projects to JPMS modules is an open challenge due to ineffective module recovery by existing architecture recovery techniques. To address this challenge, this paper presents ClassLAR (Class-and Language model-based Architectural Recovery), a novel, lightweight, and efficient approach that recovers Java modules from monolithic Java systems using fully-qualified class names. ClassLAR leverages language models to extract semantic information from package and class names, capturing both structural and functional intent. In evaluations across 20 popular Java projects, ClassLAR outperformed all state-of-the-art techniques in architectural-level similarity metrics while achieving execution times that were 3.99 to 10.50 times faster.