arXiv cs.AI· Koutian Wu, Zesen Huang, Hejia Geng·· 13 小时前AI 评分31
Git 记录不了什么：两个 AI 辅助科研仓库中的溯源可读性
What Git Does Not Record: Provenance Legibility in Two AI-Assisted Research Repositories
AI 导读
一项对同一作者两个 AI 辅助科研仓库的审计发现，Git 仓库无法可靠反映 AI 参与程度：规范性痕迹（常驻规则文件）85.6% 的历史代码行在当前版本可见，叙事性痕迹（agent 草稿本）仅 21.8%，但按修订计两者差距远小（41 个修订中分别有 15 和 18 个不留可见行）。
正文 · 原文
Abstract:Publishers and funders increasingly ask authors to disclose how AI tools contributed to a piece of research. In computational work the repository is where an author or an auditor would look for the answer, and we ask what it can actually supply. We audit two single-investigator repositories by the same author in the same field, each carrying a different class of agent residue: a prescriptive trace of standing rule files and a narrative trace of a running agent scratchpad, in repositories of 466 and 103 commits. The two are legible in opposite ways. 85.6% of the lines ever committed to the prescriptive trace are visible at the current revision, and a standing rule states a conclusion and discards the episode behind it; the narrative trace records episodes and shows 21.8%. Counted by revision the gap is far smaller: 15 of the prescriptive trace's 41 revisions leave no visible line, against 18 of the narrative trace's 41. The Co-Authored-By trailer, the field an automated audit reads, is one of three AI trailer keys Project A carries and covers 66 of the 121 commits carrying any. In Project B it has low sensitivity against an explicit within-repository proxy: 39 commits revise a file maintained to hold an agent's working notes and 1 (2.6%) carries the trailer. Project A's repository-level rate is unstable in time too, stepping from 2.7% to 17.7% across a boundary we did not specify in advance. Repository channels disagree, and neither rate can be read as an involvement rate; we do not isolate the cause, and say so. We give a field-by-field account of which provenance claims such traces support, which they cannot, and which they answer confidently and wrongly, construct an auditable evidence ledger, and derive the requirements this places on any system meant to record research provenance as it happens.
| Comments: | Accepted at the NeurIPS 2026 Workshop on AI-Native Academia. 12 pages, 4 figures. Case studies are two atmospheric and ocean science research repositories |
| Subjects: | Digital Libraries (cs.DL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.28655 [cs.DL] |
| (or arXiv:2610.28655v1 [cs.DL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28655 arXiv-issued DOI via DataCite |
Submission history
From: Koutian Wu [view email]
[v1]
Fri, 9 Oct 2026 05:43:17 UTC (43 KB)
来源：arXiv cs.AI · arxiv.org