# Thesis restated: small models need external knowledge; a harness built around a small model's real capabilities, tuned for the app user > Living preprint · as of 2026-10-25 · map node D-215 (decision) · interim record, not a final result. - [D-215] 2026-10-25 · Thesis restated: small models need external knowledge; a harness built around a small model's real capabilities, tuned for the app user — decision: State the thesis as: small models need external knowledge; we learned that and built a harness around a small model's real capabilities, tuned for the app user's experience; the conditional closing-test numbers are its evidence and honest limits. · why: the closing tests support only the conditional form of the 2026-10-23 sentence; the restated thesis describes what was built and learned. · status: kept ## Outgoing - uses: [G-conditional-thesis] conditional thesis (the conditional numbers are its evidence and limits) → https://r4topunk.github.io/boar-research/map/g-conditional-thesis.md - uses: [G-quickmath] QuickMath (part of the harness) → https://r4topunk.github.io/boar-research/map/g-quickmath.md ## Incoming - led to: [D-170] Thesis to present with the app: right whenever the content is in a pack; app built for it (superseded: the thesis restated) → https://r4topunk.github.io/boar-research/map/d-170.md - led to: [D-170] Thesis to present with the app: right whenever the content is in a pack; app built for it (superseded) → https://r4topunk.github.io/boar-research/map/d-170.md Read chapter 14, Closing the research: what a small model needs: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. - [F-1704] PACKPROOF pooled correct-any with pack installed vs without. 0.48 vs 0.26, Δ +0.23 (outcome-label share) · set 180 pack self-tests (written from the packs), dev (dev (pack-written self-tests), development data) · judge Claude Haiku 5.5-low labels; correct-any · n 180 · seeds 42 · CI CI +0.16..+0.31; n 180; seed 42 · date 2026-10-23 · caveat: self-tests favour the pack; hosts differ by arm; 1 seed Metric: outcome-label shares of n items (Claude Haiku 5.5-low labels, UXMATRIX protocol); not the judge.v1 ratio. - [F-1705] Correct-any when own article is kept vs not. 0.65 (n 98) vs 0.28 (outcome-label share) · set 180 pack self-tests (written from the packs), dev (development data) · judge Claude Haiku labels · n 180 · seeds UNKNOWN · CI n 180 · date 2026-10-23 · caveat: "about 2 in 3 when delivered" | 'kept' = own article kept (article level), between-item split, n 98 kept. - [F-1706] Own article delivered (kept) 54 % ; cited 28 % · set 180 pack self-tests (written from the packs), dev (development data) · judge 0-LLM funnel · n 180 · seeds UNKNOWN · CI n 180 · date 2026-10-23 · caveat: delivery = bottleneck | 'kept' here is article-level (own article in the kept list), not the chunk-level delivery used for MAIN facts since 10-22 ; do not mix with the 42/92 chunk-level count. - [F-1707] Packs reaching the 0.75 "proves" bar. 0 of 9; 7 below 0.60 (not default-eligible by rule); best 0.60 (two Q&A packs), worst factbook 0.25 · set 180 pack self-tests (written from the packs), dev (development data) · judge Claude Haiku · n 20 · seeds UNKNOWN · CI n 20 per pack · date 2026-10-23 · caveat: health packs AI-reviewed, not clinically reviewed AI-reviewed, not clinically reviewed. - [F-2080] Pack self-test gain does not reproduce on real items. self-test fact-added cell +0.139 (+0.075..+0.201) n 27 vs real −0.010 (−0.077..+0.050) n 10 · set self-tests (pack-written) vs MAIN keyed (dev) (dev (pack-written self-tests), development data) · judge Claude Haiku · n UNKNOWN · seeds UNKNOWN · CI 1 seed · date 2026-10-21 · caveat: post hoc; small n on real - [F-2236] The author restated the thesis on 2026-10-25: small models need external knowledge; the project learned that and built a harness around a small model's real capabilities, tuned for the app user's experience (health gate, QuickMath, pack search and delivery, the Succinct persona, a fixed check-the-source line, refusal behaviour). It replaces the 2026-10-23 sentence "right whenever the content is in a pack" as the thesis statement; the conditional closing-test numbers are its evidence and its limits. thesis statement (author, 2026-10-25) · set UNKNOWN (status UNKNOWN) · judge UNKNOWN · n UNKNOWN · seeds UNKNOWN · CI not computed · date 2026-10-25 · caveat: who: author; a framing statement, not a measurement. Evidence: with the matching pack the 1.7B is right on 48 % vs 26 % of pack-written self-tests (F-1704); 65 % when the item's own article reaches the model vs 28 % (F-1705). Limits: the article is delivered on 54 % (F-1706); no pack reached the 0.75 bar (F-1707); no gain on real development items (F-2080). Never "the harness makes it half as good". --- 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.