Episode 20: Reproducing the Pipeline
3 parts
The single-PC pipeline, the PostgreSQL schema, and how to download and verify the corpus yourself. Each part builds on the last — investigative analysis drawn from court filings, financial records, and released documents. Browse all episodes or the full investigation archive.
- Part 1 Single PC Pipeline Infrastructure
The entire 2.1 million document Epstein corpus was processed on a single Windows PC: an Intel i9-13950HX with 24 cores, an NVIDIA RTX 4070 with 8 GB of...
- Part 2 PostgreSQL Schema Infrastructure
PostgreSQL 16 serves as the single master database for the entire Epstein corpus analysis. Six core tables hold 2.1 million documents, 2.38 million enti...
- Part 3 Download and Verify Infrastructure
The corpus audit script (Script 27) audits the entire corpus in 17 seconds, cross-referencing 2.1 million database records against files on disk across...