Editorial routing shapes how computational results are qualified in AI-assisted scientific writing

2026-09-13

AI Summary

研究探讨了在AI辅助科学写作中，编辑路由如何影响计算结果的表述，并通过实验发现特定的放置规则可以恢复句子级别的资格说明。

Abstract

Large language models increasingly analyze computational results and draft manuscripts, making reliable communication as important as correct analysis. Using fixed computational evidence, we tested whether assigning comparisons across modeling choices elsewhere in a research workflow changes manuscript reporting. In constrained sentence-writing tasks, Anthropic's Claude Sonnet 5 often omitted numerical qualifications when detailed comparisons were assigned to a group repository, but retained them more often when the same comparison was assigned to Supporting Information or its own working notes; Claude Opus 5 was less sensitive. These effects did not follow a simple accessibility ordering. A targeted placement rule largely restored sentence-level qualification, whereas a generic accuracy reminder did not. Longer contributions retained numerical qualifications, although some summaries across computational settings were still redirected to the repository. Thus, documenting context within an AI workflow does not ensure its communication where readers encounter the result.

Problem

• editorial routing
• AI-assisted scientific writing
• computational results
• manuscript reporting
• research workflow

Innovation

• editorial routing
• qualifications in reporting
• large language models
• computational results
• AI-assisted scientific writing