Indicator: “Decoherence Media, a non-profit investigative outlet, recently published the Epstein Photo Network, which it described as “the highest-quality publicly available facial recognition interface to the Epstein Library, with the most verified names and the fewest false positives.” Along with creating the freely-accessible site, Decoherence’s announcement included the methodology and code used to build the tool. The post also discussed about how they dealt with false positives and incorporated manual review to try and ensure data quality. It’s a nice case study of building a facial recognition pipeline using publicly-available images. I reached out to Decoherence cofounder Tristan Lee to talk about the process and what they learned. Here’s a quick Q&A…”