claude de1cb40456 router/semantic: slice 20 pretrained fine-tune report — in-pool best, LOFO 1.000
cointegrated/rubert-tiny fine-tuned end-to-end: pair ordering 0.933-0.970
(+0.56-0.78 margin, in-pool) beats every from-scratch config, but the
held-out capability-question family fires 126/126 as action on all 18
config/seeds (FA_rate 1.000, mean proba 0.86-0.99, family σ 0.0045). tiny2
ceiling (newer, larger vocab) does not move LOFO (1.000) and is worse
in-pool. sparse 0.667 remains the safety floor; supervised encoder scaling
ruled out for the generator boundary.
2026-09-07 21:40:53 +04:00
2026-07-03 00:32:48 +02:00
S
Description
No description provided
70 MiB
Languages
Go 97.1%
HTML 0.9%
Shell 0.6%
CSS 0.5%
Makefile 0.3%
Other 0.6%