# QREWRITE: QREWRITE

> Living preprint · as of 2026-10-25 · map node X-385 (experiment) · interim record, not a final result.

<!-- lint:exempt:start -->
- [X-385] QREWRITE · QREWRITE · question: Ceiling of question rewriting (oracle) · result: MAIN 42→51 (+9 < +10); ST kept 100→118 (+18 < +20) · set MAIN 97; 180 self-tests, judge replay · verdict: closed (NO-CEILING (stopped at stage 0))

<!-- lint:exempt:end -->
Read chapter 14, Closing the research: what a small model needs: https://r4topunk.github.io/boar-research/research/closure.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-2053] QREWRITE: Ceiling of question rewriting (oracle) MAIN 42→51 (+9 < +10); ST kept 100→118 (+18 < +20) · set MAIN 97; 180 self-tests (dev (pack-written self-tests), development data) · judge replay · n UNKNOWN · seeds UNKNOWN · CI not computed · date 2026-10-23 · caveat: criterion frozen: yes (60fdc688); arm verdict: NO-CEILING (stopped at stage 0)

<!-- 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.