SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 13, 2026 · UTC

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 note

Read original source ↗ Open in workspace

recordType

paper

region

Global