PageLedgerOpen-source research software
Open-source Python CLI for auditable OCR and document-extraction runs, with page-level provenance, quality signals, budgets, review queues, and reproducible reruns.
Loading...
Eurasia in data. Archives in code.
Digital Humanities · Investigations · Trade
How nations define themselves in the post-Soviet space. My BPhil thesis examined Bashkir nationalists negotiating with Bolsheviks in 1917-1920.
Energy sector investment, sanctions policy, and commerce between the US, Europe, and Eurasian states.
Digitizing Soviet census tables using vision-language models and creating spatial datasets that track changing administrative boundaries over a century.
Python tools for geospatial analysis, NLP for Russian-language sources, and web applications that make research data accessible.
Open-source Python CLI for auditable OCR and document-extraction runs, with page-level provenance, quality signals, budgets, review queues, and reproducible reruns.
Native plant finder for wholesale buyers and restoration professionals: React/MapLibre UI, Express/GraphQL API, PostGIS spatial queries, PMTiles maps, and a Python data pipeline.
Corpus linguistics toolkit for Soviet census methodology texts (1926-1989): VLM extraction, orthography canonicalization, lemmatization, concordance, keyword, and register analysis.
Demographic study of Tatarstan: population trends, ethnic composition, and health indicators from Russian statistical data.
Interested in Eurasia, investigations, trade, or digital humanities? I'm glad to connect with researchers, analysts, investors, and collaborators. I'm available for full-time roles.