Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.00924 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908744781135872 |
|---|---|
| author | Folea, Rares Iacob, Radu Slusanschi, Emil Rebedea, Traian |
| author_facet | Folea, Rares Iacob, Radu Slusanschi, Emil Rebedea, Traian |
| contents | This paper presents a generic method for transforming the source code of various algorithms to numerical embeddings, by dynamically analysing the behaviour of computer programs against different inputs and by tailoring multiple generic complexity functions for the analysed metrics. The used algorithms embeddings are based on r-Complexity . Using the proposed code embeddings, we present an implementation of the XGBoost algorithm that achieves an average F1-score on a multi-label dataset with 11 classes, built using real-world code snippets submitted for programming competitions on the Codeforces platform. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_00924 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Complexity-based code embeddings Folea, Rares Iacob, Radu Slusanschi, Emil Rebedea, Traian Machine Learning Artificial Intelligence This paper presents a generic method for transforming the source code of various algorithms to numerical embeddings, by dynamically analysing the behaviour of computer programs against different inputs and by tailoring multiple generic complexity functions for the analysed metrics. The used algorithms embeddings are based on r-Complexity . Using the proposed code embeddings, we present an implementation of the XGBoost algorithm that achieves an average F1-score on a multi-label dataset with 11 classes, built using real-world code snippets submitted for programming competitions on the Codeforces platform. |
| title | Complexity-based code embeddings |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2601.00924 |