Decision ·
Pivot to Knowledge Packs; primary metric = in-pack conditional ratio
From the record
- Context
- Author's direction: Knowledge Packs; research question becomes conditional quality with the matching pack installed
- Why
- the product is a small model + user-selected packs; the unconditional bar was not moving
- What followed
- P1–P4, pack workflow, pack stack
- Reversible
- yes
- Status
- kept
- Alternatives considered
- stay on the bar
- keep deep-tier sweeps; non-Wikipedia corpus
Linked facts · 2
- Pivot research to Knowledge Packs (product line) (why: bar levers exhausted on ≤ 12 GB; packs help users even if not the bar)Pivot research to Knowledge Packs (product line) (why: bar levers exhausted on ≤ 12 GB; packs help users even if not the bar)Date2026-10-12Kinda record, not a measurement (set, status, judge, n, seeds: not recorded)Caveatoutcome: 11 packs published; X2b foundSourcenot in the public repositories yetOpen the data file
- Pivot to Knowledge Packs; primary metric = in-pack conditional ratio — why: the product is a small model + user-selected packs; the unconditional bar was not moving — outcome: P1–P4, pack workflow, pack stackPivot to Knowledge Packs; primary metric = in-pack conditional ratio — why: the product is a small model + user-selected packs; the unconditional bar was not moving — outcome: P1–P4, pack workflow, pack stackDate2026-10-12 20:06Kinda record, not a measurement (set, status, judge, n, seeds: not recorded)Sourcenot in the public repositories yetOpen the data file