Loss-reweighting results: q/control 0.944 (CI crosses 1), q/ctrl_random 0.985 — small non-significant causal demotion; freq corr invariant (r~-0.66) across all 9 models; blog section 8 + results.md section 3 filled honestly

1 files changed, 27 insertions, 3 deletions

diff --git a/results.md b/results.md
index 48c1c48..afb130e 100644
--- a/results.md
+++ b/results.md
@@ -124,9 +124,33 @@ read with that caveat until it lands.
 Three models per seed, identical init + minibatch order: 'q' targets weighted
 x2 in the loss, plain control, and a same-total-loss control upweighting random
 non-'q' targets. Question: does raising effective frequency causally reduce
-'q's faithful J-lens norm? PENDING — run completes within hours of this file
-being written; the summary table is printed by
-`python3 src/loss_reweight.py --step summary --layers 2,3,4`.
+'q's faithful J-lens norm? Faithful lens norm of 'q' (mean over layers 2-4):
+
+```
+  seed | q(2x)  control  ctrl_random | q/control  q/ctrl_random
+  0    | 0.0163  0.0174   0.0152    |   0.934       1.069
+  1    | 0.0150  0.0171   0.0161    |   0.881       0.932
+  2    | 0.0161  0.0158   0.0169    |   1.019       0.952
+```
+
+Cross-seed: q/control mean = 0.944 (bootstrap 95% CI [0.881, 1.019]),
+q/ctrl_random mean = 0.985 (CI [0.932, 1.069]).
+
+Reading:
+1. Expected-direction signal, small: 2x loss pressure lowers 'q' norm in 2/3
+   seeds (~5.6% mean vs control), but CI crosses 1.0 and the effect vanishes
+   vs the random-upweight control (0.985). Not a robust causal demotion at
+   this power.
+2. Frequency correlation is invariant across all 9 models: mean r = -0.66
+   (min -0.685, max -0.626) in every mode/seed/layer — training with 'q'
+   upweighted does not change the correlation structure (geometric, per the
+   W_U decomposition).
+3. Contrast: doubling ACTUAL corpus occurrences of 'q' (original ablation)
+   dropped its norm 67%; doubling its LOSS weight drops it ~6%. Data-frequency
+   is the strong causal lever; gradient reweighting under AdamW is weak
+   (adaptive per-param scaling absorbs part of the signal).
+4. Absolute norms differ across experiments (base L3 q = 0.0109 vs these
+   0.015-0.018) — only within-experiment comparisons are meaningful.
 
 ## 4. Historical / do-not-copy