Metraipolis › archive › dc_dbc698bef2b9

Lost in the Latent Space: How Code Embeddings Represent Functional Intent and Implementation Fidelity — arXiv:2610.39519

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39519
License (as archived)
CC0-1.0
Archived
2026-10-31T06:17:22.769Z
SHA-256 of the archived text
c90563ae5086bb231daed7b930510d82482f768702112bab668fbb0a6c5cd78b
Stable URL of this page
https://metraipolis.com/documento/dc_dbc698bef2b9

How to cite

Lost in the Latent Space: How Code Embeddings Represent Functional Intent and Implementation Fidelity — arXiv:2610.39519 — arXiv (en), https://arxiv.org/abs/2610.39519 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dbc698bef2b9 (Metraipolis archive dc_dbc698bef2b9, sha256 c90563ae5086bb231daed7b930510d82482f768702112bab668fbb0a6c5cd78b)
BibTeX
@misc{dcdbc698bef2b9,
  title = {Lost in the Latent Space: How Code Embeddings Represent Functional Intent and Implementation Fidelity — arXiv:2610.39519},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39519},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dbc698bef2b9; sha256 c90563ae5086bb231daed7b930510d82482f768702112bab668fbb0a6c5cd78b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39519. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Code embedding models have become a key building block for many software engineering applications, yet their internal representations remain poorly understood. Existing evaluations tend to focus on downstream task performance, offering limited insight into whether a single embedding can support both functional abstraction and implementation-sensitive analysis. To address this gap, we present a large-scale empirical study of 14 state-of-the-art code embedding models. We evaluate their representational behavior through three complementary analyses: supervised probing for functional abstraction and implementation fidelity, zero-shot retrieval experiments to assess geometric similarity, and controlled perturbation experiments that measure embedding responses to semantics-preserving code transformations. The results reveal a consistent abstraction-fidelity tension: models that better preserve stylistic and structural signals tend to do so at the expense of semantic generalization, while models with similar retrieval performance can nevertheless respond very differently to the same implementation changes. Overall, our findings suggest that a single universal code representation remains out of reach, motivating more representation-aware evaluation, selection, and deployment of code embedding models in software engineering.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE) ; Computation and Language (cs.CL); Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2610.39519 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T06:07:23.409Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).