diff --git a/STATUS.md b/STATUS.md
index cd64dfc..989c9f2 100644
--- a/STATUS.md
+++ b/STATUS.md
@@ -3,6 +3,21 @@
 Checkpoint for the standalone desktop app. Prepend a new dated section per
 material change; keep history below.
 
+## 2026-09-16 — open-item audit; Large v3 provisioning verified
+
+- **Large v3 first-use download verified end-to-end** in an isolated
+  `HF_HUB_CACHE`: `snapshot_download` fetched 2.9 GB in ~2.5 min,
+  `is_model_downloaded('large-v3')` → True, model loaded in 4.6 s
+  (CPU int8) and transcribed a real clip. Note: `setup-standalone.sh`
+  vendors only **Base**; Large v3 is deliberately a first-use auto-download
+  into the `models/hf-cache` the app exports — the registry's
+  `download_instructions()` already covers the manual path. No defect.
+- Skipped backend test resolved: intentional (`test_ai_adapters.py:55`
+  skips when faster-whisper IS installed — the missing-dep path can't be
+  exercised then). Not a Postgres test. Current count: 80 passed, 1 skipped.
+- Earlier open items 1–2 (startup job adoption, upload-mapping reuse) were
+  closed by `ba54cb8` + the `.shonar.json` sidecar.
+
 ## 2026-09-15 (evening) — summarize progress bar, job adoption
 
 **Committed:** `7fa99e8` streaming summarize progress, `ba54cb8` job adoption.
@@ -61,13 +76,11 @@ narrowed to Base + Large v3; Debian packaging + install guide; standalone
 provisioning with vendored base model.
 
 **Open items / candidates:**
-1. Startup adoption of engine jobs already running (app restart currently
-   orphans them from the UI).
-2. Reuse upload mapping after restart instead of re-uploading.
-3. Investigate the 1 skipped backend test (likely the Postgres-path test).
-4. Confirm Large v3 one-command provisioning on a fresh machine.
-5. Stale-noise cleanup: `~/.config/shonar-desktop/pump-error.log` holds old
+1. Stale-noise cleanup: `~/.config/shonar-desktop/pump-error.log` holds old
    Android→server upload 404s (pre-desktop pivot); no action taken.
+2. Optional: full-length Large v3 transcription timing (300 s clip ran well
+   under 7 min on CPU int8 while the app + LLM were also active; a quiet
+   benchmark would pin the number).
 
 **Known debt:** none blocking. No dead stubs; one former TODO (search
 backend) resolved by deletion.