From b24ffe67a200853bd9e397beaae682777deacb28 Mon Sep 17 00:00:00 2001
From: Daniel Maddern <daniel.maddern@illuvium.io>
Date: Thu, 13 Aug 2026 16:57:44 +0700
Subject: [PATCH] Record sampler wrapper boundary fix

---
 PARITY.md | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/PARITY.md b/PARITY.md
index 3d743ad..5922c45 100644
--- a/PARITY.md
+++ b/PARITY.md
@@ -189,7 +189,7 @@ gate and is exact.
 | Beta/RES sampler | Yes | H3 replay is bit-exact for all 12 captured sampler calls and RES update is bit-exact from captured denoised; direct raw-output to model-wrapper denoised conversion retains small BF16/state boundary deltas |
 | Video VAE decoder | Yes | Same final sampled latent decoded through direct VAE versus Comfy PNG frames: mean abs pixel delta `0.0833898`, max `6` |
 | Audio VAE/decode/mux | No | Preview intentionally produces video only |
-| End-to-end prompt-only FL2VA preview | Yes | Direct 320x192x22 dragon smoke videos generated with Sage2. Comfy-equivalent CPU joint AV seed initialization now matches captured `initial.pt` exactly; seed-exact direct MP4 versus Comfy PNG frames still has mean abs pixel delta `14.0714`, max `193`, consistent with the remaining model-wrapper denoised conversion boundary |
+| End-to-end prompt-only FL2VA preview | Yes | Direct 320x192x22 dragon smoke videos generated with Sage2. Comfy-equivalent CPU joint AV seed initialization matches captured `initial.pt` exactly. Video-side wrapper denoised conversion is exact after BF16 raw-output materialization; remaining seed-exact final-latent delta is localized to regenerated text conditioning plus audio-side wrapper conversion |
 | Full Ref2VA | No | References, vision conditioning, VAE encode, audio, and muxing are unimplemented |
 
 ## Remaining Gates, In Dependency Order
@@ -199,10 +199,10 @@ unless the checkpoint, Comfy version, prompt, or backend changes.
 
 1. **Final video latent layout.** Compare direct `unpatchify_video` output
    with Comfy before entering the sampler.
-2. **Model-wrapper denoised conversion.** Direct H3 and RES update gates pass,
-   and direct initial AV noise now matches Comfy exactly. Close the remaining
-   small `h3_output -> denoised` conversion delta before claiming identical
-   seed output.
+2. **Text/audio end-to-end closure.** Direct H3, video wrapper conversion,
+   RES update, VAE decode, and initial AV noise now match their captures.
+   Close regenerated text conditioning and audio-side wrapper conversion before
+   claiming identical seed output.
 3. **Feature/performance work.** Only then add audio, Ref2VA/reference paths,
     Sage3, CUDA graphs, and multi-GPU execution.