自动化审计的天花板由什么决定:从通用代码到科学代码的结果与数据分析
What Moves the Ceiling on Automated Audit: from General Code to Scientific Code, Results and Data
AI 导读
一项 arXiv 研究分析了跨厂商模型审计员加确定性检查的自动化审计安排的能力上限。
正文 · 原文
Abstract:Models increasingly check what other models write. We study one shipped arrangement, in which an auditor from a different vendor reads the work and deterministic checks verify what code can verify, and measure its limits against ground truth no model supplies. On general-purpose code with hidden tests, eight readings of the auditor reach 30.0% recall [20.0, 40.7] at 16.0% [10.1, 22.3] flags on correct code, with diminishing returns and no plateau. The reading model (confounded with its sampling), one rulebook sentence and the decision rule each move that figure, and much of what is missed is, on a post hoc rating, behaviour the specification never determined. In three preregistered science studies, checking that reported numbers trace to their sources flagged all 49 inconsistent reports and none of 25 consistent fabrications, of which the model auditor flagged 23 (21 with a sound finding, post hoc); on data, a documentation-derived validator and the auditor flagged overlapping but different faulty items, together 112 of 140 at a 2.9% [0.7, 5.7] flag rate on clean data; and on scientific code, reframing the task around one step cut flags on correct code from 68.7% to 36.0%. Where both tiers ran, the deterministic one flagged no clean item and could not see consistent error; the model saw some and erred itself. Studies making model calls were preregistered, the two unregistered analyses are named, and every quoted report passed independent cross-vendor review.
| Comments: | 27 pages, 4 figures, 1 table |
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.23250 [cs.SE] |
| (or arXiv:2611.23250v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2611.23250 arXiv-issued DOI via DataCite |
Submission history
From: Zhaohe Dong [view email]
[v1]
Thu, 24 Sep 2026 07:43:25 UTC (128 KB)
来源:arXiv cs.AI · arxiv.org