Skip to content
RFJ
The Library

The Corpus

The source material this notebook is built on. Every ruling cited here must trace back to one of these four buckets.

Corpus state · live
52
Curated
23
Books
83
Articles
23
YouTube
181
Total entries

Each entry is a typed JSON record in /content/, ready to be embedded into the Phase 2 retrieval index. The trust ranking surfaces curated entries first.

The four buckets, ranked

BucketTrustVolumeEffort to add
Hand-curatedHighestSmallestHigh
Books (PDF)HighMediumMedium
Web articlesHighMediumLow
YouTube transcriptsMediumLargestLowest (auto)

Phase 2 retrieval will weight these accordingly: a hand-curated quote outranks a YouTube transcript every time, even if both address the same question.

The pipeline

  1. Source identified — book, lecture URL, article URL.
  2. Captured — PDF saved locally; transcript scraped or fetched; article archived (with permalink + capture date).
  3. Indexed — chunked, embedded, stored. The index is private and not republished.
  4. Vetted — for the hand-curated bucket, I read the quote in full context and tag it with a confidence note.
  5. Retrieved — Phase 2 surfaces matches against questions with citation back to the original.
Ask