paper: interim directionality fig (app:directionality) + confound TODO

route2 deploy hack collapses for ANY v_grad (real/placebo/Haar) but solve tracks
direction (real>placebo>Haar). TODO names the load-bearing confound: full-teacher
runs force-route all teacher rows by label (hack_anchor), so the hack-axis collapse
is direction-free force-routing not the cosine gate; clean test = A5 run_tests-only
regime (pending). n=1 interim.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
This commit is contained in:
wassname
2026-06-05 23:40:02 +00:00
co-authored by Claudypoo
parent 329066e99b
commit f82a4f034d
5 changed files with 102 additions and 0 deletions
+7
View File
@@ -0,0 +1,7 @@
arm,direction_type,subspace,deploy_hack,deploy_solve,n,job
vanilla,none,na,0.323,0.484,3,keynote
real_v,real,in,0.000,0.625,1,nofloor_s41
null_city_s41,placebo,in,0.000,0.531,1,86
null_city_s42,placebo,in,0.000,0.578,1,117
vampire,placebo,in,0.000,0.547,1,115
haar_d0,random,out,0.094,0.516,1,114
1 arm direction_type subspace deploy_hack deploy_solve n job
2 vanilla none na 0.323 0.484 3 keynote
3 real_v real in 0.000 0.625 1 nofloor_s41
4 null_city_s41 placebo in 0.000 0.531 1 86
5 null_city_s42 placebo in 0.000 0.578 1 117
6 vampire placebo in 0.000 0.547 1 115
7 haar_d0 random out 0.094 0.516 1 114