Metraipolis › archive › dc_56599d00dc10

ShikumiMiner: Mining Recurring Implementation Patterns in AI Codebases — arXiv:2609.02789

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02789
License (as archived)
CC0-1.0
Archived
2026-10-17T05:14:03.060Z
SHA-256 of the archived text
a26a6fd12586dd33b86704d5d4aea03d07ae1c1a74d1daaa35474d92bff48130
Stable URL of this page
https://metraipolis.com/documento/dc_56599d00dc10

How to cite

ShikumiMiner: Mining Recurring Implementation Patterns in AI Codebases — arXiv:2609.02789 — arXiv (en), https://arxiv.org/abs/2609.02789 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_56599d00dc10 (Metraipolis archive dc_56599d00dc10, sha256 a26a6fd12586dd33b86704d5d4aea03d07ae1c1a74d1daaa35474d92bff48130)
BibTeX
@misc{dc56599d00dc10,
  title = {ShikumiMiner: Mining Recurring Implementation Patterns in AI Codebases — arXiv:2609.02789},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02789},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_56599d00dc10; sha256 a26a6fd12586dd33b86704d5d4aea03d07ae1c1a74d1daaa35474d92bff48130},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02789. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models are paving the way towards innovation by understanding, analyzing, summarizing and generating content in the modern world. Currently there are thousands of LLM projects developed by engineers in open-source repositories. However, whether these LLM projects have underlying patterns or not remains a question. Exploring these underlying patterns will give new dimensions to the developers who aim to develop these LLM projects. In this paper, we propose ShikumiMiner, a static-analysis framework that combines Abstract Syntax Tree (AST) and Control Flow Graph (CFG) features to detect and compare recurring implementation patterns in C++ local LLM codebases. We analyze ten GitHub open-source repositories and classify functions into seven study-specific categories using a multi-label Random Forest model. Studying these patterns can provide useful insights for developers aiming to design LLM applications.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-03 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.02789 — 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 2026-10-17T04:25:46.778Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).