P4: NOTES — fit exploration results (mask-level fits do not transfer to full render)

- sqrt-Hann analysis regressed (0.788/2.91) vs committed Hann-Hann (0.774/2.12).
- Full-corpus G/W/A/rp mask-level fit (0.66) regressed in OLA render (0.812/2.37);
  the render metric is the only honest one.
- Residuals level-dependent (t1k_b1f loud +0.8..2.9, al low -1.1..-1.8); solution =
  structural A/B/gamma band LUT, combine/acc 0x5407c8 + FFT-conv 0x535a70 (todo #3).
This commit is contained in:
2026-08-20 19:34:01 +03:00
parent cc52461903
commit 067d483f15
+17
View File
@@ -992,3 +992,20 @@ Root cause of t1k_b1f residual (+2.1 loud) and al low-level (-1.8): NOT LUT cap
setters, not DSP scalar setters) - static decode exhausted for now. setters, not DSP scalar setters) - static decode exhausted for now.
NEXT: wire combine/accumulator 0x5407c8 + FFT-conv 0x535a70 into the chain (structural, may NEXT: wire combine/accumulator 0x5407c8 + FFT-conv 0x535a70 into the chain (structural, may
close the t1k_b1f/al tail by smoothing the mask) - todo #3. close the t1k_b1f/al tail by smoothing the mask) - todo #3.
## ============ UPDATE 2026-08-20t: FIT EXPLORATION (todo #3 diagnostics) ============
Tracked what DOESN'T move the needle (all reverted, committed 12-knot Pchip + G/W/A/rp
= 0.9963/0.3335/0.9807/0.0275/0.2159 remains optimal, corpus mean|err| 0.774 max 2.12):
1. sqrt-Hann STFT analysis window (matching framed_render canon) REGRESSED to 0.788 max
2.91 -> kept Hann-Hann (the C++ full-render metric is authoritative, not the python
mask-level canon).
2. Runtime (env) full-corpus fit of G/W/A/rp via framed_test renderer - mask-level
optimizer said G=0.877/W=0.402/A=0.673/rp0=0.0041/drp=0.28 (mean 0.66 mask-level) but
FULL RENDER regressed to 0.812 max 2.37 -> reverted. Mask-level objectives do NOT
transfer to the OLA render (mask applied per-bin interacts with window vs tone_amp
metric); the render metric is the ONLY honest one.
3. Residuals are level-dependent (t1k_b1f loud +0.8..2.9, al low -1.1..-1.8, everything
else <=0.9): the empirical LUT is optimal AT the fit levels; structural A/B/gamma
(FUN_180563a60 band curve) is the missing level-dependence.
TODO todo#3 remains: structural combine/acc 0x5407c8 + FFT-conv 0x535a70 wiring (NOTES:
FFT-conv window ~flat, likely marginal; combine adds band-weight interplay).