From 5b56c8fbbf5875e4aa31761ed47636a72f6aa409 Mon Sep 17 00:00:00 2001
From: Tinnci <23432137+Tinnci@users.noreply.github.com>
Date: Sun, 12 Jul 2026 18:28:14 +0800
Subject: [PATCH] Mark LavaSR roadmap evidence complete

---
 ROADMAP.md | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/ROADMAP.md b/ROADMAP.md
index 48b0564..f7006e6 100644
--- a/ROADMAP.md
+++ b/ROADMAP.md
@@ -30,7 +30,7 @@ Release-preparation status:
 Release scope deliberately excludes new heavyweight evaluators, new model weights, and a new
 self-contained backend.
 
-## Priority 1: Stabilize LavaSR With Broader Evidence
+## Completed: Stabilize LavaSR With Broader Evidence
 
 `lavasr-compat` should not be marked stable from a single parity path. The next validation slice is:
 
@@ -49,6 +49,12 @@ Promotion criteria:
 - passing stability and parity evidence on the supported runtime path;
 - known limitations visible in model listings.
 
+The release-tag and follow-up T4 workflows now cover verified real weights, CUDA smoke, failure-case
+matrices, strict digital-silence preservation, deterministic repeated inference, versioned
+regression thresholds, and same-backend parity across refs. The backend remains experimental because
+real-speech full-reference metrics did not justify stable promotion, not because the stability
+evidence is missing.
+
 ## Completed: Produce Real Evaluation Evidence
 
 The harness is implemented; the missing value is a repeatable evidence set.