Metraipolis › archive › dc_fe8005eaa2e5
Hybrid Source Code Change Impact Analysis — arXiv:2611.10958
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.10958
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:42:57.662Z
- SHA-256 of the archived text
f5a83e4c282d2a82ab6d42ed72c51c63c18c4c41c1ef628a244afd75513b4183- Stable URL of this page
https://metraipolis.com/documento/dc_fe8005eaa2e5
How to cite
Hybrid Source Code Change Impact Analysis — arXiv:2611.10958 — arXiv (en), https://arxiv.org/abs/2611.10958 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fe8005eaa2e5 (Metraipolis archive dc_fe8005eaa2e5, sha256 f5a83e4c282d2a82ab6d42ed72c51c63c18c4c41c1ef628a244afd75513b4183)
BibTeX
@misc{dcfe8005eaa2e5,
title = {Hybrid Source Code Change Impact Analysis — arXiv:2611.10958},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.10958},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fe8005eaa2e5; sha256 f5a83e4c282d2a82ab6d42ed72c51c63c18c4c41c1ef628a244afd75513b4183},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10958. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Change impact analysis (CIA) helps developers identify code entities impacted by their initial changes. While several approaches for CIA were proposed, they still struggle with either low precision or low recall, thereby increasing manual effort for developers to verify the results. Furthermore, limitations in the used datasets and experimental setups can bias the results reported by many CIA approaches. In this paper, we first address the dataset limitations by manually labeling 1,931 changed code entities stemming from 263 commits of 22 open-source Java projects. Next, we introduce two variants of katIA, our code change impact analysis approach that combines static impact analysis with the reasoning capabilities of large language models (LLMs). The first variant uses a single prompt (katIA-SP) for refining an initial static impact set while the second variant uses three specialized agents (katIA-MA). The evaluation with our curated dataset shows that katIA-SP with Gemini 2.5 Flash achieved an F1-score of 22.4% when matching impacted entities by their fully qualified names (FQN) and 27.0% when matching them by their class and entity names (CE). The latter shows an improvement of 2.0 percentage points over the state-of-the-art. This score is further improved by katIA-MA which, using Gemini 2.5 Flash, yields an FQN-matching F1-score of 29.1% and a CE-matching F1-score of 33.3%. While these improvements come at the cost of increased median generation time from 0.570 s to 11.214 s and median token usage from 1,235 to 6,462 tokens, the improved performance justifies the additional cost. The comparison of three LLMs using katIA-SP finds that Gemini 2.5 Flash is the most consistent model. These results indicate that combining static impact analysis with LLM-based refinement, particularly with the multi-agent variant, can improve code change impact analysis. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.10958 — 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 2026-11-10T18:37:37.617Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).