A dashboard for observing U.S. State Deptartment post counts

Detects content changes in 383 federal government documents using Wayback Machine captures. Updated weekly.

Archive and report government documents to the GPO.

Multi-archiver forensic audit of the 2024 End Of Term web crawl. Deduplicating billions of government records.

Pipeline turning archival PDFs into compact, structured evidence packages that open-source AI models can use directly. Tests whether evidence packaging materially improves open-tier table reasoning on Internet Archive collections.