Public sources enter the pipeline
Government data, archive tables, public datasets, CSV files, JSON feeds, and source pages are converted into local research assets.
Evidence systems lab
Research data pipeline
A controlled interface for the technical layer behind the site: acquisition, normalization, source triage, anomaly review, and publication into maps, dashboards, record panels, and reproducible update commands.
Names, dates, coordinates, and categories
Records are aligned across place names, time intervals, source labels, layer types, and confidence levels before they enter a map.
Human review remains decisive
AI-assisted triage can flag anomalies or extraction candidates, but source status, historical claim, and publication quality stay review-controlled.
Interfaces make the system visible
The final output is a set of maps, dashboards, record panels, review consoles, and reproducible update commands.
Geocoded conflict-system records condensed into map-ready research layers.
UNHCR public statistics rendered as origin, asylum, and IDP layers.
USGS, NASA EONET, and GDACS records normalized into a risk atlas.
A reproducible local pipeline refreshes conflict, displacement, and disaster datasets.