diff options
Diffstat (limited to 'notes/40_reproduction_manifest.md')
| -rw-r--r-- | notes/40_reproduction_manifest.md | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/notes/40_reproduction_manifest.md b/notes/40_reproduction_manifest.md index 7e18d98..009f058 100644 --- a/notes/40_reproduction_manifest.md +++ b/notes/40_reproduction_manifest.md @@ -31,7 +31,7 @@ deterministic given the seeds shown. Long runs use `nohup`. | claim | command | outputs | note | |---|---|---|---| -| `E_B[e_0]=0.4378+/-0.008` vs hidden share 0.4403; per-width errors <= 0.008 | `python scripts/actual_fa_initial_operator_moments.py --widths 16 24 32 48 64 96 --init-seeds 6 --feedback-samples 512 --torch-threads 8 --outdir outputs/actual_fa_initial_operator_moments` | `actual_fa_initial_operator_moments/` | 29 | +| no-fit erosion = hidden share, max abs error <= 0.008 across 6 widths x 6 inits (predicted span 0.15-0.45); "0.4378/0.4403" headline retired (note 37 ยง4) | `python scripts/actual_fa_initial_operator_moments.py --widths 16 24 32 48 64 96 --init-seeds 6 --feedback-samples 512 --torch-threads 8 --outdir outputs/actual_fa_initial_operator_moments` | `actual_fa_initial_operator_moments/` | 29, 42 | | e0 exactly Gaussian; KS p 0.13-0.999; sampler = real FA backward, linear identity <= 8.9e-16 | `python scripts/actual_fa_initial_erosion_distribution.py --widths 16 32 64 128 --init-seeds 3 --feedback-samples 4096 --torch-threads 8 --outdir outputs/actual_fa_initial_erosion_distribution` | `actual_fa_initial_erosion_distribution/` (pre-fix snapshot kept in `*_pre_fix_backup/`) | 32, 37 | ## Finite-time chain (lazy validity -> drift -> estimator) |