Stage 19 prerequisite: derive and pin the hold-out split; gold oracle passes 905/905

↗ view on GitHub · Eli Ziff · 2026-07-31 · 2d0e8bbb

deriveSplitTests continues the mini walk past every document the mini
derivation touched (including one truncated at the cap), so the split is
document-blocked by construction; setup asserts zero overlap against the
pinned mini corpus rather than trusting it. Hold-out: 3 sources, 55 docs,
582 tests - privacy_qa mini IS the complete upstream benchmark (194/194)
and yields no hold-out, recorded in derivation.sources_without_split.

Gates, run before any model call: gold oracle 905/905 on the normalized
load (contractnli 276, cuad 311, maud 318) and 587/905 with --raw (maud
0/318), so normalization is load-bearing here too; db-level re-check on
a2aj-holdout-lf.sqlite also 905/905. CR census reproduces the upstream
signature on unseen documents: 18/18 maud files carry \r, the other two
sources clean.

Mini re-derives byte-identical to its pinned manifest (73 files).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01H9ToHYJVDxfeJcJwdzrP2H
Repository eliziff/Beaver
Author Eli Ziff <eliasziff@gmail.com>
Authored
Parents 15b15d2d
Stats 6 files changed , +592 , -39
Part of Legal grounding and retrieval research

Capture this commit into my fork

Download a Markdown prompt that tells Claude how to port this exact commit into your working tree. Run it via claude -p < capture-commit-2d0e8bbb.md from inside the repo you want the change in.

⬇ Download capture-commit-2d0e8bbb.md