SLM-418: render replay preference rows into trainable pairs (DSH5-10) - #1124

Closed

Tyler-R-Kendrick wants to merge 3 commits into

mainfrom

claude/great-dirac-ni43oh

Commits on Jul 27, 2026

SLM-418: render replay preference rows into trainable pairs (DSH5-10)
claude
committed
df5fa56
SLM-418: build a demo replay-preference pairs corpus + run it (DSH5-10) (#1125)

Tyler-R-Kendrick
and
claude
authored
a6b3ed4
SLM-418: first step onto the DSH3 typed policy target (DSH5-10) (#1127)

Tyler-R-Kendrick
and
claude
authored
cfc9a3c