Matiq/soothe2-re
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

P4: F2 structural wiring tests — combine+FFT-conv naive wiring both regress (doc only)

Browse Source 
Wiring FFT-conv step5 (mask*=win) gives mean 5.2, combine/acc (att/rel from kRTAtt/
kRTRel) gives 4.7 vs base 0.75-0.80 on representative subset. Both belong to the
exp2(mask) structural chain (blend 0.8 + bigkernel) NOT the fitted bridge final-gain.
No code change; bridge + Pchip stays canonical (0.773).
This commit is contained in:
Matiq
2026-08-20 20:52:00 +03:00
parent 1cfe013939
commit fa1ef205df
1 changed files with 17 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
handoff/NOTES_LEVEL.md
+17
View File
@@ -1060,3 +1060,20 @@ FULL honest 24-bit corpus (59 cases) inside ONE fixed bridge pipeline
F1 (params of the LUT curve) is hereby CLOSED as "already produced, none accepted"; F1 (params of the LUT curve) is hereby CLOSED as "already produced, none accepted";
the structural A/B/gamma from ctx+0x188 remains the only path to bytes (blocked: the structural A/B/gamma from ctx+0x188 remains the only path to bytes (blocked:
level-path object not live-captured; see F2/F5.) level-path object not live-captured; see F2/F5.)
## ============ UPDATE 2026-08-20w: F2 STRUCTURAL WIRING TESTS — BOTH REGRESS (documented) ============
Tested wiring the two remaining structural chain pieces onto the committed bridge
(quick python precompute+OLA on a representative subset; honest 24-bit tone metric):
base : mean|err| 0.75-0.80, max 2.1
FFT-conv step5 (mask *= win8193 0.5->1.0) : mean 5.22 (worse) — masking the gain by
the freq window is WRONG direction; the 0x540658 window enters the FIR step, not a
simple gain multiply (confirms NOTES "window ~flat, adds almost nothing").
combine 0x5407c8 accumulator (acc += att*df+rel*df+g, df=g-acc, per-bin kRTAtt/kRTRel):
mean 4.68 (worse) — naive acc toward 2.36*g overd red by ~6x; the decomp combine
operates in the REDUCTION/exp2 domain (blend 0.8 pedestal + bigkernel exp2), NOT on
the fitted bridge final-gain. Mismatched domain => not a valid wiring test.
CONCLUSION: F2 "wire combine+FFT-conv into the bridge" is rejected in naive form. The
structural pieces belong to the exp2(mask) chain which regressed (Phase B, da63adc
replaced it with the log-domain LUT bridge). The bridge (Pchip, 0.773) remains canonical.
Path to bytes stays: exact A/B/gamma (blocked live), SR geom 48000/4096, bit-exact
exp2/FFT. No code change made this session; NOTE-only.