Commit Graph

2 Commits

Author SHA1 Message Date
wassname 4fb7b59548 plot(tufte): route-evidence figure — drop legend/grid/box, direct value labels
Eraser test: direct end-labels carry name+value (no legend, no separate
annotations, no gridlines). Layering: hack=red dominates (the story), solve=
muted grey recedes. Range-frame left spine, minimal ticks (0/.5/1, 0/19).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-05-30 03:22:35 +00:00
wassname 3004b23f74 feat: route-evidence figure — training hack vs shipped hack (single run)
Visualizes #182: model hacks ~0.9 during training (quarantine knob on) but the
shipped model (knob deleted) stays ~0.25 at preserved solve ~0.5. The train-vs-
ship gap is the routing benefit. Reads old(hack_abl)+new(hack_ship) ship cols.
out/route_evidence_s41.png committed (-f, gitignored dir).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-05-30 03:17:35 +00:00