Proximity is measured over citations between two papers we both hold, weighted by how heavily one leans on the other, and is symmetric — it does not distinguish citing from being cited. Authors without a profile here are skipped, and a genuinely close colleague can be missing simply because their work is not in our arXiv corpus. Method: docs/06-citations-pipeline.md.
Papers
(1 of 4)
An automatic finite-sample robustness metric: when can dropping a little data change conclusions? Part I: definitions and experiments
published2026 · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · 9 citations · first circulated 2020
Assembled from arXiv and OpenAlex. Duplicate records for the same paper are merged, and the published version is shown where we could identify one. Corrections welcome.