About the hub
The corpus hub is the public registry of reference corpora for XERJ's reference-coding workflow — and for any agent that must answer from pinned, current, licenced text instead of memory.
Every corpus passes seven gates
| gate | what satisfies it |
|---|---|
| G1 domain | the row finishes "an agent working on ___ would query this for ___" in one specific sentence |
| G2 shape | the retrieval unit matches the question: clause-level sections for standards, function bodies for code, advisory records for precedent |
| G3 un-memorisation | answer-bearing content is niche/internal/post-cutoff/too detailed for recall — famous-and-small is killed as retrieval theatre |
| G4 licence | a human opened the licence at the pin and wrote the review block; detector output is a hint, never the verdict |
| G5 pin truth | manifest SHA = the commit the build used; rewrites are withdrawals, not re-pins |
| G6 registry validation | validate_hub.py green in CI on the corpus-hub branch |
| G7 retrieval spot-check | 5 pre-registered domain queries, top-5 graded manually; median ≥ 3 relevant to pass |
Scores on the cards
G7 is the retrieval spot-check above. A/B is the drift-anchored agent benchmark: the same task run bare (offline, instructed to answer honestly rather than fabricate) and with the corpus; the badge shows pass counts (bare → corpus). A tie is a publishable outcome; the registry records it either way.
Rights policy
Per-source licence verdicts live in each manifest's review block. PD (US government works), OGL v3.0 (UK),
and permissive licences ship as adapt-with-attribution; GPL/AGPL/SSPL and other restrictive
sources are approach-only — readable as design evidence, never copied. Closed families
(ICC I-codes, Eurocodes, NEC/ASTM/ISO/DIN) are documented as closed and excluded.
Contribute
The registry is a git branch: corpus-hub.
Read CONTRIBUTING.md
and the program doc (PROGRAM-100.md). This site is generated from the registry by
tools/corpus-hub-site/gen.py — no hand-written corpus pages, ever.