Files
kgilper-krea-reference/docs
Kevin Gilper e8a97d0dcf Stage 3 render-derivation: shipped style table measures best; layers are second-order
Ran a render-based derivation for the style role on the model: held the real
style settings fixed, varied only the 12 layers across seven candidates,
rendered and scored look-transfer minus subject-leak.

- The shipped STYLE table scored best (objective 0.106); the shallow-tap table
  was worst - render evidence supports spiking the effective deep taps.
- But differences were small and every output was nearly the same bowl: at
  realistic style settings the layer table is a second-order knob. The primary
  look-vs-subject control is strength and the shape/global split.

Bottom line committed to the README: the reliable way to set the layers is
render-based measurement (conditioning analysis alone misleads); applying it
shows the shipped tables are directionally right and, for the style role,
near-optimal. The durable deliverable is the render harness, which can
re-derive or verify the layers for any future checkpoint. Full result + images
in local_records.
2026-07-03 07:50:48 -04:00
..