n=500 controls: paired net-effect significant (loop vs untrained merge 17-4, p=0.007); ladder and net accounting finalized

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Nils
2026-07-14 20:08:57 +02:00
co-authored by Claude Fable 5
parent 1d4cffd6ad
commit 0fd93cb328
8 changed files with 10160 additions and 19 deletions
+4 -7
View File
@@ -100,13 +100,10 @@ def fig_ladder():
_, h0 = ev(OUT / "eval_code_code_s0_full.json", 0)
add("base (k=0, exact)", h0, NH, GRAY)
# untrained E2B control (250-item era, n_hard=28)
d = json.load(open(OUT / "eval_code_untrained.json"))
hu = max(v["by_label"]["hard"] for k, v in d["ks"].items() if k != "0")
add("untrained loop (best k)", hu, 28, GRAY)
d = json.load(open(OUT / "eval_code_ff.json"))
add("trained FF (no recurrence)", d["ks"]["1"]["by_label"]["hard"], 28,
ORANGE)
_, hu = ev(OUT / "eval_code_untrained_full.json", 4)
add("untrained loop (perturbation floor)", hu, NH, GRAY)
_, hf = ev(OUT / "eval_code_code_ff_full.json", 1)
add("trained FF (no recurrence)", hf, NH, ORANGE)
_, hp = ev(OUT / "eval_code_pause16.json", 1)
add("pause-16 registers (width)", hp, NH, ORANGE)
_, hl = ev(OUT / "eval_code_code_s0_full.json", 4)