Metraipolis › archive › dc_885774ec4e70
Launder-Bench: Can Repository-Level Agentic Code Laundering Be Detected? — arXiv:2611.01966
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01966
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:18:18.764Z
- SHA-256 of the archived text
02cf7b7d535fad0dc9c397bc7f68b6a0ef0dbbcf6d8d8115918d50632c05c531- Stable URL of this page
https://metraipolis.com/documento/dc_885774ec4e70
How to cite
Launder-Bench: Can Repository-Level Agentic Code Laundering Be Detected? — arXiv:2611.01966 — arXiv (en), https://arxiv.org/abs/2611.01966 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_885774ec4e70 (Metraipolis archive dc_885774ec4e70, sha256 02cf7b7d535fad0dc9c397bc7f68b6a0ef0dbbcf6d8d8115918d50632c05c531)
BibTeX
@misc{dc885774ec4e70,
title = {Launder-Bench: Can Repository-Level Agentic Code Laundering Be Detected? — arXiv:2611.01966},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01966},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_885774ec4e70; sha256 02cf7b7d535fad0dc9c397bc7f68b6a0ef0dbbcf6d8d8115918d50632c05c531},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01966. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Coding agents can now rewrite repository-scale codebases while preserving tested behavior, creating a new challenge for plagiarism detection, license auditing, and software provenance. We ask whether such rewrites can still be traced to their source. Existing clone benchmarks emphasize fragments and bounded edits, while repository-transformation benchmarks evaluate functional correctness rather than provenance. Moreover, ranking the most similar source does not establish derivation when independent implementations can be similarly close. We define repository-level agentic code laundering and introduce Launder-Bench, to our knowledge the first repository-level benchmark for provenance under agentic rewriting, constructed from 282 real-world repositories. A source-hidden reconstruction protocol decomposes source behavior, reconstructs modules and repository structure, and retains rewrites only after execution-based verification. We evaluate the same provenance problem in two complementary settings: Launder-Bench-Pair contains 1,128 pairwise instances asking whether two repositories share provenance, while Launder-Bench-Attr contains 229 source-attribution instances asking which candidate is the source, with abstention when evidence is insufficient. Measured same-domain independent repositories establish how much similarity can arise without shared provenance and provide detector-specific reference bands. Existing methods remain far from saturating Launder-Bench: the strongest static method reaches only 0.66 AUROC on pairwise detection, while repository encoders rank the true source first on up to 22% of attribution queries but earn calibrated attribution credit on only 1-2%. These results reveal a systematic gap between relative code similarity and source-specific provenance evidence, providing a reproducible target for provenance detection under agentic rewriting. 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/2611.01966 — 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 2026-11-03T18:09:53.642Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).