# 14 · Closing the research: what a small model needs > Closed record · research record 1.0 · as of 2026-10-25 16:46; the author closed the research lines on 2026-10-23. Current standing, not a final result: Open fronts: https://r4topunk.github.io/boar-research/data/status.json. > > Final · as of 2026-10-25 16:46 · 0 of 71 wins on the phone, U-total 0.165 (Claude) / 0.242 (gpt-5.6-sol), below the 0.50 bar - Page: https://r4topunk.github.io/boar-research/research/closure/ · Markdown twin: https://r4topunk.github.io/boar-research/research/closure.md · Whole paper: https://r4topunk.github.io/boar-research/llms-full.txt · Index: https://r4topunk.github.io/boar-research/llms.txt - Span: 2026-10-23 → 10-24 **In one sentence.** On 2026-10-23 the author closed the research lines; on 2026-10-25 he stated the thesis the record presents: **small models need external knowledge, and the project, having learned that, built a harness around a small model's real capabilities, tuned for the app user's experience** (a health gate, QuickMath, pack search and delivery, the Succinct persona, a fixed check-the-source line, refusal behaviour) [F-2236] [D-215]. The closing tests are its evidence and its honest limits: with the matching pack the 1.7B is right on 48 % of pack-written self-tests vs 26 % without, and on 65 % when the item's own article reaches the model vs 28 % otherwise; but the article arrives only 54 % of the time, no pack reached the 0.75 bar fixed in advance, and the gain did not transfer to real development items. The sentence the author first wrote on 2026-10-23, "right whenever the content is in a pack", is kept as the hypothesis those tests checked: they support it only in that conditional form. The afternoon turned to content (reshaping packs), the night to validating one closed engine, and the next day's judge kept the shortest answer style. ## For curious readers {#curious} #### Research closed, a sentence tested On 23 October the author closed the research and wrote down what he expected: "the app is right whenever the answer is in one of its libraries". Then we tested that sentence. #### Right two times in three, when the page arrives On each library's own questions, the small model was right 48 % of the time with the library installed and 26 % without. When search delivered the right article, it was right 65 % of the time, but search delivered it only about half the time. No library reached the 75 % mark we had fixed in advance. *Badge:* 180 questions written from 9 libraries · practice · Claude Haiku answer labels (not the old ratio) · 1 run · desktop. #### What we learned, and what we built The tests support that first sentence only in a narrower form: right about two times in three when the right page reaches the model. On real questions, the libraries did not help in a measurable way. What the author takes from it, and states as the thesis (25 October 2026): small models need outside knowledge, so the app is a harness built around what a small model can really do: a safe text instead of a guess on health, sums done by code, a search that brings the right page, one short answer style, a line asking you to check the source, and a fixed refusal text where it should not guess. The numbers above are its evidence and its limits; they do not make the app half as good as the frontier. *Badge:* the author's statement, not a measurement. #### Short answers win Longer answer styles were right just as often as the short one, but shown wrong without a warning about twice as often. The short style stayed. *Badge:* 60 practice questions · Claude Haiku labels · 1 run. **In one sentence card:** "A small model needs a library: right about two times in three when the page arrives; the page arrives about half the time." *Facts: [F-1653] [F-1690] [F-1704] [F-1705] [F-1706] [F-1707] [F-2236] [D-215] [G-conditional-thesis] [F-2080] [F-1727] [F-1728]* ## For tech people {#tech} ### Acceptance tests on a desktop twin, one closed engine, a judge pass the next morning After the author closed the research lines (2026-10-23 11:53), the remaining work was acceptance tests on the app's desktop twin, scored with outcome labels (Claude Haiku 5.5-low; correct-any = right with the right source shown + right from memory; WU = wrong with no warning). PACKPROOF (180 pack-written self-tests of 9 packs, 1.7B Succinct, seed 42): correct-any 0.48 with the pack vs 0.26 without, 0.65 when the item's own article is kept (54 % of items), 0 of 9 packs at 0.75. UXMATRIX (60 dev items): Succinct beats Detailed with and without the pack; with the pack off every honest "unknown" is an engine decline. Pack shaping (factbook rewritten as short sentences that name the country) doubled fact delivery (7 → 15 of 20) and correct answers (5 → 10) on its own self-tests, but missed its frozen rule by one new warned confident error. Overnight one closed tree, ENGINE-RC (SEFIX-124 + W78 + shaped factbook + a reworded banner), passed every 0-LLM suite (identity 97/97 and 180/180, routes 103/110, the one letter-FAIL pre-existing) and generated 2,855 answers with no judge call; the next day's judge kept Succinct (correct-any 0.43 vs 0.42 for longer styles, wrong-unwarned 0.12 vs 0.23–0.25). **Fix box:** a false "Not found in this phone's offline library" line showed on 37 of 97 answers that had kept passages; after the fix, 0 [F-1725]. **Thesis box (the author, 2026-10-25; [F-2236], [D-215]):** "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 harness in the shipped app: the health gate (fixed safe text when no health source is kept), QuickMath (conversions and arithmetic in code), pack search and delivery (the ported bench search, ON_NO_HEALTH), the Succinct persona, the fixed line "May contain errors; check the source." and fixed-text refusals (T18). Evidence: 48 % vs 26 % with the matching pack and 65 % vs 28 % when the article reaches the model (pack-written self-tests, Haiku labels, one seed). Limits: delivered on 54 %; 0 of 9 packs at 0.75; no gain on real dev items [F-2080]; the app's desktop-twin ruler reading is below the bar (T15). The 2026-10-23 sentence ("right whenever the content is in a pack") is the hypothesis these tests checked. Never "the harness makes it half as good" (U41). ## For AI professionals {#ai} ### The record for this chapter **Key facts (outcome-label shares unless named; Claude Haiku 5.5-low labels; Qwen3-1.7B, Succinct; seed 42; desktop twin, no phone; dev):** - Closure: the author closed the research lines; the rest is acceptance tests on the app's desktop twin [F-1653] [D-167] [D-169]. - Thesis, first form (2026-10-23 12:19): "right whenever the content is in a knowledge pack, and the app built to answer well under that premise" ([D-170] / [F-1690]); the closing tests support it only in the conditional form [G-conditional-thesis]. Superseded as the thesis statement on 2026-10-25 ([D-215] / [F-2236]): small models need external knowledge; a harness built around a small model's real capabilities, tuned for the app user. Its limits include the real-item split: the self-test fact-added cell +0.139 (+0.075…+0.201, n 27) vs real development items −0.010 (−0.077…+0.050, n 10) (Haiku judge.v1 U, one seed; [F-2080]), and the app's desktop-twin ruler reading (lower family 0.164, below the bar; [F-2215]). - PACKPROOF (180 pack-written self-tests of 9 packs): correct-any 0.48 with the pack vs 0.26 without, +0.23 (+0.16…+0.31) [F-1704]; 0.65 when the item's own article is kept (n 98) vs 0.28 [F-1705]; the own article is kept for 54 % and cited for 28 % (article-level; [F-1706]); 0 of 9 packs reach 0.75 (best 0.60, worst 0.25; [F-1707]). Without the pack: wrong and confident 0.17, wrong under the warning line 0.45, honest "unknown" 0.12 [F-1708]. - UXMATRIX (60 dev items): Succinct beats Detailed with and without the pack (correct-any ON 0.35 vs about 0.27; [F-1709], [F-1710]); with the pack off the model never says "I don't know" itself: every honest "unknown" is an engine decline, and the warning line shows on 75 % of answers [F-1711]. - Pack and search levers closed the same day (0-LLM replays): undelivered facts are a search problem, 44 of 50 already in K13 [F-2100]; dropping the Wikipedia packs loses MAIN facts 42 → 33, so they stay [F-1714] [D-172]; an oracle question rewrite would deliver only +9 facts (bar +10) [F-1715]; warning cited-but-unsupported answers would catch 9 of 26 wrong at a cost of 5 of 37 correct, NO [F-1712]. - CONTENT-FIRST (author, 15:3x): no model change; make the right chunk reach the 1.7B [D-174]. Shaped factbook (short sentences that name the country, no new facts): fact chunk kept 7 → 15 of 20; correct 5 → 10 of 20 (two seeds, Haiku); Opus judge.v1 U 0.316 → 0.436 (+0.121, +0.030…+0.221, two seeds); NOT-CONFIRMED by its frozen rule because of one new warned confident error [F-2104]. The 0.436 here is a factbook self-test U and has nothing to do with the deep tier's 0.436 on V-para. - ENGINE-RC (night, one closed tree): every 0-LLM suite passed (identity 97/97 and 180/180; routes 103/110; the one letter-FAIL pre-existed); data read per question 125.09 → 21.26 MB; a false "Not found in this phone's offline library" line on 37 of 97 answers with kept passages fell to 0; 2,855 answers generated, 0 judge calls overnight [F-2105] [F-1722] [F-1725] [F-1726]. - Validation judge (2026-10-24, the page's numbers): Succinct correct-any 0.43 with the pack (right with source shown 0.30, wrong-unwarned 0.12), 0.22 without (wrong-unwarned 0.10); longer styles (one 4–5-sentence paragraph, two paragraphs) were right as often (0.42) but doubled wrong-unwarned answers (0.23, 0.25) [F-1727] [F-1728] [F-2106]. Follow-ups: carrying the subject brings the turn-1 source back (0.083 → 0.708) without changing accuracy (0.458 both) [F-1729] [F-2107]. The 10-23 → 10-24 Succinct shift (0.35 → 0.43) has no isolated cause in the record (engine changed in between; n 60, one seed). **Key decisions:** [D-215] (thesis restated, 2026-10-25), [D-167], [D-168] (adopted for delivery: SEFIX-124, W78, Succinct for models ≤ 2 GB, Deep Research hidden), [D-169], [D-170], [D-171], [D-172], [D-173], [D-174], [D-175] (shaped factbook stays user-selected, unpublished), [D-176], [D-177] (wider append budget and best retrieval config stay out: dose/number probes changed), [D-179], [D-180]. **Turning point:** 2026-10-23 11:53, the author closes the research lines; at 12:19 a first thesis is stated, and by 14:2x the tests have reduced it to its conditional form; on 2026-10-25 the author restates the thesis as what was learned and built, with those numbers as its evidence and limits. ### 6.10 Small models need external knowledge: what the closing tests support The author closed the research lines on 2026-10-23 with the hypothesis "right whenever the content is in a pack" [D-167] [D-170]; on 2026-10-25 he stated the thesis as a design statement: small models need external knowledge, and the project built a harness around a small model's real capabilities, tuned for the app user's experience [F-2236] [D-215]. The numbers below are its evidence and its limits; they do not establish a quality level (U41–U43). Closing tests ran on the desktop twin with outcome labels (Claude Haiku 5.5-low; §2.13 of the claims page): on 180 pack-written self-tests of 9 packs (1.7B Succinct, seed 42), correct-any is 0.48 with the pack vs 0.26 without (+0.23, +0.16…+0.31); 0.65 when the item's own article is kept (n 98) vs 0.28; the own article is kept on 54 % and cited on 28 % (article level); 0 of 9 packs reach the 0.75 bar fixed in advance ([F-1704]…[F-1708]). The hypothesis therefore holds only in the conditional form, and on real development items the pack gain does not transfer (fact-added cell −0.010, −0.077…+0.050, n 10, vs +0.139 on self-tests; [F-2080]). Pack shaping (factbook) doubled delivery and correct answers on 20 self-tests and moved Opus U 0.316 → 0.436 (+0.121, +0.030…+0.221), NOT-CONFIRMED by one new warned confident error [F-2104]. The closed engine passed every 0-LLM validation suite and cut data read per question 125.09 → 21.26 MB [F-2105] [F-1722]. The 2026-10-24 validation judge kept Succinct: correct-any 0.43 vs 0.42 for longer styles, wrong-unwarned 0.12 vs 0.23–0.25 (UXMATRIX 60, seed 42) [F-1727] [F-1728]; the Succinct reading moved from 0.35 on 10-23 to 0.43 on 10-24 on the same items after engine changes, with no isolated cause. Subject carry restored the turn-1 source on follow-ups (0.083 → 0.708) without changing accuracy (0.458) [F-1729]. ## 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-1653] Author closes research lines; CLOSING-TESTS plan. · date 2026-10-23 - [F-1690] Thesis to present with the app: right whenever the content is in a pack; app built for it. PACKPROOF supports only a conditional form (65 % when delivered) · set UNKNOWN (status UNKNOWN) · judge UNKNOWN · n UNKNOWN · seeds UNKNOWN · CI not computed · date 2026-10-23 · caveat: who: author; why: product framing; reversible: yes (framing) · later: 2026-10-25: the author restated the thesis (small models need external knowledge; a harness built around a small model's real capabilities); this sentence stays quoted as the hypothesis the closing tests checked. - [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-1708] Without the pack: wrong-confident / wrong-warned / honest-unknown. 0.17 / 0.45 / 0.12; refused-wrongly 0 · set 180 pack self-tests (written from the packs), dev (development data) · judge Claude Haiku · n 180 · seeds UNKNOWN · CI n 180 · date 2026-10-23 · caveat: honesty comes from the warning line, not from abstention - [F-1709] UXMATRIX Succinct: correct-any ON / OFF. 0.35 / 0.28 (CWS 0.28 / 0.03; WC 0.22 / 0.07) (outcome-label share) · set 60 dev items (40 cooking/money, 15 delivered general, 5 no-pack) (dev, development data) · judge Claude Haiku; outcome shares · n 60 · seeds 42 · CI n 60; seed 42 · date 2026-10-23 · caveat: Succinct and Detailed on different hosts Metric: outcome-label shares of n items (Claude Haiku 5.5-low labels, UXMATRIX protocol); not the judge.v1 ratio. - [F-1710] UXMATRIX Detailed: correct-any ON / OFF. about 0.27 / 0.17 (headline rounding; the CWS + CFM cells sum to 0.26 / 0.16); WC OFF 0.15 (outcome-label share) · set 60 dev items (40 cooking/money, 15 delivered general, 5 no-pack) (development data) · judge Claude Haiku · n 60 · seeds 42 · CI n 60; seed 42 · date 2026-10-23 · caveat: Deep arms not run (scope cut) Metric: outcome-label shares of n items (Claude Haiku 5.5-low labels, UXMATRIX protocol); not the judge.v1 ratio. - [F-1711] With pack off the model never says "I don't know" itself; all HU are engine declines; warning line shown OFF. 75 % (Succinct), 63 % (Detailed) · set 60 dev items (40 cooking/money, 15 delivered general, 5 no-pack) (development data) · judge Claude Haiku + 0-LLM · n 60 · seeds UNKNOWN · CI n 60 · date 2026-10-23 · caveat: 6 of the declines are health false alarms on cooking/money AI-reviewed, not clinically reviewed. - [F-1712] WARN-KEPT: confident errors with pack on all keep a citation; lexical rule warns 9/26 at 5/37 correct cost. NO · set UXMATRIX traces + MAIN 97 (dev, development data) · judge 0-LLM · n 26 · seeds UNKNOWN · CI n 26 / 37 · date 2026-10-23 · caveat: errors are misreadings of a relevant chunk - [F-1714] NOWIKI: kit without Wikipedia packs. 42 -> 33 MAIN facts; 10 public v0.1 items lost; topics anchor 25 -> 11; health: 1 self-test + 1 topics item lost (MAIN health losses 0) · set dev (dev, development data) · judge 0-LLM · n 97 · seeds UNKNOWN · CI n 97 / 180 / 27 · date 2026-10-23 · caveat: verdict KEEP AI-reviewed, not clinically reviewed. - [F-1715] QREWRITE oracle ceiling (answer-form query) MAIN 42→51 (+9 < +10); self-tests kept 100→118 (+18 < +20) · set dev (dev, development data) · judge 0-LLM · n 97 · seeds UNKNOWN · CI n 97 / 180 · date 2026-10-23 · caveat: oracle uses answer terms the user lacks - [F-1722] ENGINE-RC reading cost (S8) 21.26 MB/question vs 125.09; ctx p50 0.978x; disk 1.06x · set UNKNOWN (status UNKNOWN) · judge 0-LLM · n UNKNOWN · seeds UNKNOWN · CI quiet desktop runs · date 2026-10-23 · caveat: desktop only, phone unmeasured - [F-1725] False "Not found in this phone's offline library" line with sources kept. 37 of 97 answers showed "Not found" although passages were kept; after the fix 0 do (1 correct "Not found" remains, on an item that keeps no source) · set MAIN dev (dev, development data) · judge 0-LLM · n 97 · seeds UNKNOWN · CI n 97 · date 2026-10-23 - [F-1726] Night generation. 25 jobs, 2,855 answers, 0 failures, 0 judge calls · set UNKNOWN (status UNKNOWN) · judge UNKNOWN · n UNKNOWN · seeds UNKNOWN · CI not computed · date 2026-10-23 · caveat: judge picked by author next day - [F-1727] Succinct on ENGINE-RC (page numbers) ON CWS 0.30, correct-any 0.43, WU 0.12; OFF correct-any 0.22, WU 0.10 (outcome-label share) · set UXMATRIX 60, dev (dev, development data) · judge Claude Haiku labels · n 60 · seeds 42 · CI n 60; seed 42 · date 2026-10-24 · caveat: PASS vs frozen CWS ≥0.28, WU OFF ≤0.10 Metric: outcome-label shares of n items (Claude Haiku 5.5-low labels, UXMATRIX protocol); not the judge.v1 ratio. - [F-1728] S+ / two-paragraph personas. correct-any ON 0.42 / 0.42; WU ON 0.23 / 0.25 (vs 0.12) (outcome-label share) · set UXMATRIX 60, dev (development data) · judge Claude Haiku · n 60 · seeds 42 · CI n 60; seed 42 · date 2026-10-24 · caveat: warning line 0.60→0.48 with longer answers Metric: outcome-label shares of n items (Claude Haiku 5.5-low labels, UXMATRIX protocol); not the judge.v1 ratio. - [F-1729] Follow-ups on ENGINE-RC, with and without subject carry. correct-any 0.458 both; on-referent 1.00; turn-1 source 0.083→0.708; WU 2→4 of 48 (outcome-label share) · set F8 dev (dev, development data) · judge Claude Haiku · n 48 · seeds 42 · CI n 48; seed 42 · date 2026-10-24 · caveat: health follow-ups 0.19 both Metric: outcome-label shares of n items (Claude Haiku 5.5-low labels, UXMATRIX protocol); not the judge.v1 ratio. 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-2100] Undelivered facts are a search problem. 44 of 50 already in the K13 kit · set dev (dev, development data) · judge 0 LLM · n UNKNOWN · seeds UNKNOWN · CI 50 items · date 2026-10-23 - [F-2104] Shaped factbook. fact chunk kept 7→15/20; correct 5→10/20; Opus U 0.316→0.436 (+0.121, +0.030..+0.221) · set factbook self-tests (pack-written) (dev (pack-written self-tests), development data) · judge Claude Haiku; Claude Opus · n UNKNOWN · seeds UNKNOWN · CI 20 items, 2 seeds · date 2026-10-23 · caveat: NOT-CONFIRMED (1 new warned CE); does not transfer to the native engine - [F-2105] ENGINE-RC passes the 0-LLM validation suites. identity 97/97 & 180/180; MAIN delivered 42; ST fact 84 vs 77; routes 103/110; 21.26 MB/q · set dev (dev, development data) · judge replay · n UNKNOWN · seeds UNKNOWN · CI not computed · date 2026-10-23 · caveat: V1 letter-FAIL pre-existing - [F-2106] Longer styles do not add correctness. Succinct WU ON 0.12 vs S+ 0.23, P2 0.25; correct-any 0.43 / 0.42 / 0.42 (outcome-label share) · set dev (dev, development data) · judge Claude Haiku · n UNKNOWN · seeds UNKNOWN · CI 60 items · date 2026-10-24 · caveat: Metric: outcome-label shares of n items (Claude Haiku 5.5-low labels, UXMATRIX protocol); not the judge.v1 ratio. - [F-2107] Follow-up accuracy is reading-limited. correct 0.458 with or without subject carry; source kept 0.08 → 0.71 with carry · set dev (dev, development data) · judge Claude Haiku · n UNKNOWN · seeds UNKNOWN · CI 48 F8 · date 2026-10-24 - [F-2215] RULER-FINAL U-total of BoarLite b4ef94f3 on v0.4: Claude family 0.164 (0.123-0.208), OpenAI gpt-5.6-sol family 0.245 (0.194-0.300); minimum over families 0.164 (0.123-0.206); win-rate 0 of 71 (Claude) and 0 of 71 with 1 tie (gpt-5.6-sol); fixed-text refusals on 3 items. Claude 0.164; gpt-5.6-sol 0.245; min 0.164; win-rate 0 (ruler U-total) · set v0.4 (held-out ruler; exposed) (held-out ruler (v0.4; exposed)) · judge Claude Opus + OpenAI gpt-5.6-sol (each vs its own references) · n 71 headline items · seeds 1 (42) · CI Claude 0.123-0.208; gpt-5.6-sol 0.194-0.300; min 0.123-0.206 · date 2026-10-24 20:34 · caveat: Metric: ruler v0.4 U-total (71 headline items, health weight 0.5); never on one axis with the judge.v1 ratio or outcome labels. Desktop twin, one seed. Published by the author's decision of 2026-10-25 (AD-15 (b)): BoarLite/LabRat is the author's own submission. History, not the headline: desktop twin of engine b4ef94f3, one seed, before the Rat persona line and the cleanup (F-2223, F-2225); not a measurement of LabRat 7788924a. The headline is the on-phone run DEVICE-FINAL (OF-8). - [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". ### Decisions cited {#decisions} - [D-167] 2026-10-23 · Close the research lines; no new arms after PLUGBATCH-SELF and STYLE-SEFIX; the rest of the work is acceptance tests · why: "we reached where we needed to"; ensure the app delivers it. · status: kept - [D-168] 2026-10-23 · Adopted for delivery: SEFIX-124 search stack + W78 reading-cost stack; Succinct for models ≤ 2 GB; Deep Research hidden; detector v3b stays; decoder/readers/gat · why: measured results of 10-22/23. · status: kept - [D-169] 2026-10-23 · Closing tests run on the desktop twin with no phone · why: phone not available. · status: kept - [D-170] 2026-10-23 · Thesis to present with the app: right whenever the content is in a pack; app built for it · why: product framing. · status: superseded by D-215 (restated by the author on 2026-10-25 (D-215); the closing tests supported this sentence only in a conditional form) - [D-171] 2026-10-23 · Defaults by rule: Succinct stays, Deep hidden, no change to the honesty surface · why: UXMATRIX matrix. · status: kept - [D-172] 2026-10-23 · Keep Wikipedia packs in the default kit K13 · why: removing them loses 9 MAIN facts, 10 general items, 2 health sources. · status: kept - [D-173] 2026-10-23 · No new packs for coverage (gaps are search, not missing content) · why: 44/50 gaps already in K13; candidate packs ≈ 1 fact each. · status: kept - [D-174] 2026-10-23 · CONTENT-FIRST: no model change; make the right chunk reach Qwen3-1.7B; build/shape the packs · why: "even the small model should answer right having the content" · status: kept - [D-175] 2026-10-23 · Shaped factbook v2: card drafted as user-selected only; publish waits for author OK · why: Opus +0.121 but one new warned CE; correct-any 0.50 < 0.60 eligibility. · status: kept - [D-176] 2026-10-23 · Night program: build ENGINE-RC as one tree, validate 0-LLM first, generate all answers, judge nothing overnight · why: validate the closed engine; judge on demand. · status: kept - [D-177] 2026-10-23 · X2B-BUDGET and RETBENCH best config stay out of ENGINE-RC · why: dose/number safety probes changed. · status: kept - [D-179] 2026-10-24 · Succinct stays the default; S+ (4-5 sentences) and two-paragraph variants rejected · why: same correctness, wrong-unwarned doubles. · status: kept - [D-180] 2026-10-24 · Subject carry on follow-ups not adopted as an accuracy fix (UX gain only) · why: 0.458 correct both arms. · status: kept - [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 --- 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.