Reproduce “A machine-readable catalogue of the Tsiolkovsky papers (fond 555, Archive of the Russian Academy of Sciences), and a way to measure how well its handwriting can be read” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Vladimir Beskorovainyi
The authors provide a searchable catalogue and machine transcriptions for Tsiolkovsky’s archive, covering 2,019 files and 51,008 scans. They compare handwritten readings with typed copies to estimate reading difficulty, not direct accuracy. Across 1,759 pairs, median word agreement is 37%. Validation in two files found 0.92 correlation in page rankings when typed readings were at least 85% accurate, but does not establish a universal error rate.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.