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

..

build_combined_pool.py

wip

2026-05-29 06:29:46 +00:00

derisk_expose_k.py

feat(stage2): T0 de-risk gate — does Qwen3-4B hardcode visible tests?

2026-05-30 02:41:14 +00:00

plot_dynamics.py

log: rename route ablated-eval -> SHIP-eval, self-evident with SHOULD

2026-05-30 03:01:04 +00:00

plot_route_evidence.py

feat: route-evidence figure — training hack vs shipped hack (single run)

2026-05-30 03:17:35 +00:00

results.py

fix(results): read ground-truth mix_ratio from log, not argv default

2026-05-30 02:24:44 +00:00