engineering/arborist
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

docs: corpus loaded is the 2010 Wikipedia snapshot, not 2003

Browse source 
fox 2026-05-21: two corpora exist (2003-05-16 + 2010); the 2010 one is
loaded in ~/.arborist/shards (verified: 866K docs/shard, has Barack
Obama / YouTube articles a 2003 dump can't). CLAUDE.md Live-endpoints and
the energy-COGS report now state 2010; fabrication-bait fixtures target
post-2010 events. Historical closed-ticket prose left as point-in-time
records.
This commit is contained in:
russell@unturf.com 2026-05-21 12:36:20 -04:00
parent b44e9255b2
commit 26e4db67d1
No known key found for this signature in database
2 changed files with 10 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

7
CLAUDE.md
View file

@ -352,7 +352,12 @@ revert without reading why. When in doubt, walk the
- LLM: `https://hermes.ai.unturf.com/v1` (Hermes-3 Llama-3.1-8B-FP8-
Dynamic on vLLM, 82K ctx, no auth). `uncloseai.com` is marketing
only. Override via `--endpoint` or `ARBORIST_LLM_ENDPOINT`.
- Wikipedia dumps: `https://dumps.wikimedia.org/archive/2003/2003-05-16/en/`.
- Wikipedia dumps: two corpora available — the 2003-05-16 cur snapshot
(`https://dumps.wikimedia.org/archive/2003/2003-05-16/en/`) and a
**2010** snapshot. **The 2010 corpus is what is currently loaded** in
`~/.arborist/shards` (866K docs/shard; contains post-2003 articles like
Barack Obama / YouTube — the discriminator). Fabrication-bait fixtures
(`qa_questions_stale_map`) target post-**2010** events.
`robots.txt` returned 404 → no rules.
### Budget discipline — Hermes / Qwen first, Opus deferred

5
docs/energy-cogs-benchmark.md
View file

@ -30,8 +30,11 @@ Two rigs:
Common to both: arborist `query()` pipeline, **STOCK V.1** frozen config
(`claim_lattice` hash `036a4c79…`, `quote` `5b6ca4c5…`,
`bench/stock_v1.py`); orchestrator drives the endpoint, power sampled on
`bench/stock_v1.py`); **Wikipedia 2010 corpus** (~866K docs/shard,
`~/.arborist/shards`); orchestrator drives the endpoint, power sampled on
the box; **$0.33/kWh** (the only non-measured input, `--price-per-kwh`).
(Fabrication-bait questions target post-2010 events, so the substrate
correctly abstains where bare models answer from parametric memory.)
**Two arms, same model (the substrate-delta design):**
- **solo** — question only, neutral system prompt, no retrieval, no verifier.