diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-04-08 18:25:49 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-04-08 18:25:49 -0500 |
| commit | 2b4581723d0c5ed562528fac6b0a789adf95e3c5 (patch) | |
| tree | 1a632390bcb385fd93c06b182b4cfb2fe31caa73 /results | |
| parent | daa0cb53cad483903f1f89a3d7d692bdc00d9827 (diff) | |
paper v2.31.8: Appendix I EP random-target ‖h_L‖ values from saved JSON
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>
Diffstat (limited to 'results')
| -rw-r--r-- | results/ep_random_h_L_summary.json | 10 |
1 files changed, 10 insertions, 0 deletions
diff --git a/results/ep_random_h_L_summary.json b/results/ep_random_h_L_summary.json new file mode 100644 index 0000000..96449e0 --- /dev/null +++ b/results/ep_random_h_L_summary.json @@ -0,0 +1,10 @@ +{ + "EP_random_5ep": { + "h_L_median": 556.95361328125, + "h_L_mean": 554.086181640625 + }, + "EP_random_100ep": { + "h_L_median": 2151.283935546875, + "h_L_mean": 2126.281982421875 + } +}
\ No newline at end of file |