faeval.git/results/ep_random_h_L_summary.json, branch master Unnamed repository; edit this file 'description' to name the repository. paper v2.31.8: Appendix I EP random-target ‖h_L‖ values from saved JSON 2026-04-08T23:25:49+00:00 YurenHao0426 Blackhao0426@gmail.com 2026-04-08T23:25:49+00:00 2b4581723d0c5ed562528fac6b0a789adf95e3c5 Appendix I claimed EP random-target ‖h_L‖ "≈586 at 5 ep" and "≈2,085 at 100 ep" without a saved-JSON source. Re-measured on the saved checkpoints with consistent methodology (model.eval(), n=2048 test median), giving 557 (5 ep) and 2151 (100 ep). The ~5% discrepancy is likely model.train() vs model.eval() LN-batch-stats; the new values are reproducible. Saved results/ep_random_h_L_summary.json as the source of truth. The "26× smaller than DFA's 14,510 at 3 ep" comparison still holds (was "25×"; updated to "26×" with the new EP values). The fixed-feedback vs energy-based separation conclusion is unchanged. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> 
Appendix I claimed EP random-target ‖h_L‖ "≈586 at 5 ep" and "≈2,085
at 100 ep" without a saved-JSON source. Re-measured on the saved
checkpoints with consistent methodology (model.eval(), n=2048 test
median), giving 557 (5 ep) and 2151 (100 ep). The ~5% discrepancy
is likely model.train() vs model.eval() LN-batch-stats; the new
values are reproducible.

Saved results/ep_random_h_L_summary.json as the source of truth.
The "26× smaller than DFA's 14,510 at 3 ep" comparison still holds
(was "25×"; updated to "26×" with the new EP values).

The fixed-feedback vs energy-based separation conclusion is unchanged.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>