# XFAM: XFAM: cross-family re-judge of the existing V-para traces

> Living preprint · as of 2026-10-25 · map node X-175 (experiment) · interim record, not a final result.

<!-- lint:exempt:start -->
- [X-175] XFAM · XFAM: cross-family re-judge of the existing V-para traces · question: Does a judge from another model family change the levels, ranking or win-rate of the 4B and deep-tier rows on V-para? · result: 4B: raw 0.497 (0.449–0.547), floor-adjusted 0.361; deep + think 512: raw 0.667 (0.621–0.711), floor-adjusted 0.577 (0.519–0.632); deep − 4B +0.171 (+0.123…+0.219) vs +0.139 under Claude; per-item Spearman 0.88–0.92; win-rate 0.00–0.01. · set V-para (dev-style), judge cross-family (OpenAI gpt-5.6-sol (via the Codex CLI)), CI 0.449…0.547 · verdict: measurement

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

- uses: [G-judge-family] judge family / self-preference (the other family scores ≈ 0.10 higher, same ranking) → https://r4topunk.github.io/boar-research/map/g-judge-family.md
- led to: [D-115] Claude judge stays the headline (lower of two judges); judge family named next to every ratio; win/tie/loss leads (the stricter judge stays the headline) → https://r4topunk.github.io/boar-research/map/d-115.md

Read chapter 10, Measuring the measurer: https://r4topunk.github.io/boar-research/research/measurer.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-017] A judge from a different model family scores everything higher on V-para, but keeps the ranking and the near-zero win-rate. 4B: raw 0.497 (0.449–0.547), floor-adjusted 0.361; deep + think 512: raw 0.667 (0.621–0.711), floor-adjusted 0.577 (0.519–0.632); deep − 4B +0.171 (+0.123…+0.219) vs +0.139 under Claude; per-item Spearman 0.88–0.92; win-rate 0.00–0.01 (judge.v1 ratio) · set V-para (dev-style, development data) · judge cross-family: OpenAI gpt-5.6-sol (via the Codex CLI) (post-hoc, not pre-registered) · n 51 (408 judge calls) · seeds 2 · CI 95 % item bootstrap (4B floor-adjusted CI not in the sources read) · date 2026-10-16 · caveat: Post-hoc and not pre-registered; it is the only point above 0.50 floor-adjusted on V-para and exists only under the cross-family judge; the lower-judge rule keeps the Claude number as headline.
- [F-1218] Cross-family judge via paid API (GPT pilot): 204-call pilot → held / withdrawn (no paid keys, no human review) (Later done by the author via Codex (XFAM))

<!-- 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.