# DEEPNORAG: DEEPNORAG

> Living preprint · as of 2026-10-25 · map node X-103 (experiment) · interim record, not a final result.

<!-- lint:exempt:start -->
- [X-103] DEEPNORAG · DEEPNORAG · question: Do the knowledge packs still matter for the deep tier with thinking 512: arm N (DT512 config with config.kit = []) vs control H = DT512 slice rows on V-para (diagnostic)? · result: −0.045 (−0.083…−0.011) · set V-para (V-para) slice 20; v0.1 (smoke, 2 items), judge Claude Haiku (L1), n 20 (signal20-vpara slice), seeds 1 (s42), CI −0.083…−0.011 · verdict: closed (closed — RETRIEVAL-MATTERS (diagnostic; stage 3 not needed since Δ ≤ −0.03))

<!-- lint:exempt:end -->
## Outgoing

- ruled out: [G-deep-tier] deep tier (the deep tier without retrieval was worse (retrieval stays)) → https://r4topunk.github.io/boar-research/map/g-deep-tier.md

Read chapter 9, Knowledge packs: https://r4topunk.github.io/boar-research/research/packs.md

## Facts cited {#facts}

Resolve every [F-…] marker in https://r4topunk.github.io/boar-research/data/facts.json. Each line gives the claim, the number with its metric family, set and status, judge, n, seeds, CI, date and caveat.

<!-- lint:exempt:start -->
- [F-1098] Retrieval removal on deep tier (DEEPNORAG): no packs → −0.045 (packs stay (diagnostic))
- [F-1117] R33 Remove retrieval from deep tier: slice 20. −0.045 (−0.083…−0.011) · set UNKNOWN (status UNKNOWN) · judge UNKNOWN · n UNKNOWN · seeds UNKNOWN · CI not computed · caveat: why closed: diagnostic: packs stay

<!-- lint:exempt:end -->
---

Cite as: r4to, independent researcher. RatLab — A Boar Research (2026), research record 1.0, as of 2026-10-25. Text and data CC BY 4.0. Fact ids or a link must travel with a quote. How to cite: https://r4topunk.github.io/boar-research/cite/ · https://r4topunk.github.io/boar-research/CITATION.cff.

AI-reviewed, not clinically reviewed. Nothing here is medical advice.