AI writing tools' impact on scientific manuscript reporting
Editorial routing shapes how computational results are qualified in AI-assisted scientific writing
This matters to researchers using AI writing tools because it shows how the placement of technical details can affect the accuracy of their manuscripts.
Researchers tested how AI tools like Anthropic's Claude Sonnet 5 and Opus 5 handle computational results in scientific writing. They found that the placement of detailed comparisons in a manuscript affects how numerical qualifications are included. For example, Claude Sonnet 5 often omitted such qualifications when comparisons were in a group repository but retained them when in Supporting Information. A targeted placement rule could restore this, but longer contributions sometimes redirected summaries elsewhere.
Editorial routing shapes how computational results are qualified in AI-assisted scientific writing
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.
