diff --git a/docs/dev/denoise.md b/docs/dev/denoise.md
index cddde95..480eb07 100644
--- a/docs/dev/denoise.md
+++ b/docs/dev/denoise.md
@@ -1,8 +1,9 @@
 # Learned denoise — joint demosaic and denoise on the mosaic
 
 Design for **FR-DEV-3g** ([requirements.md](requirements.md)), the learned stage
-[outstanding.md §3](outstanding.md) says is missing. Draft of 2026-09-27: nothing here is built,
-and every figure marked *estimate* is waiting for the measurement that replaces it.
+[outstanding.md §3](outstanding.md) says is missing. Drafted 2026-09-27; a first version shipped
+in 0.21.0, and §11 records what was built and measured. Figures still marked *estimate* are
+waiting for the measurement that replaces them.
 
 ---
 
@@ -288,17 +289,27 @@ is ~120 MB, and a derived file inside a synced tree is exactly what
   with progress over the canvas — the same pattern as a photograph that is only on the server.
 - Export needs the result and computes it if the cache has lost it.
 
-### 7.2 The Amount control
+### 7.2 The grain control
 
-A Denoise toggle and one Amount slider in develop. Moving the slider runs inference on the
-**visible viewport only** (~1 MP, a fraction of a second — *estimate*) so the photographer judges
-on the real result; releasing it queues the whole frame. There is no per-frame blend between the
-two paths: blending the classical output back in re-adds the noise the network removed.
+What shipped is a switch and a **Keep grain** slider, not the Amount described first. The slider
+blends the two demosaics per pixel — but only the *brightness* of their difference: `out =
+denoised + grain · ΔY / wb`, with `ΔY` the luminance of `wb · (classical − denoised)`. Taken after
+the as-shot balance and handed back divided by it, the grain is neutral in the finished picture.
+
+The objection that stood here — that blending the classical output back in re-adds the noise —
+holds for a plain mix, which also brings back the classical path's colour speckle and false
+colour. A luminance-only blend returns film-like grain and nothing else, and it needs no
+inference: one elementwise GPU pass (`dr_gpu::GrainBlend`) per slider value, producing a new
+source the adjust pass draws. Comparing the two on real 6D frames, the user chose this one.
+
+The σ-map Amount (§3.3) still works — `NoiseModel::scaled` — and stays available for a later
+"strength" control; its cost is a re-run of the network.
 
 ### 7.3 Runtime
 
-Through `dr-inference-engine`, as the other models run ([inference.md](inference.md)): TensorRT or
-CUDA fp16 on the laptop, MIGraphX on the desktop, ORT CPU everywhere, QNN on the tablet. Work is
+Through `dr-inference-engine`, as the other models run ([inference.md](inference.md)), as
+`Role::Denoiser`: TensorRT or CUDA fp16 on the laptop, MIGraphX on the desktop, ORT CPU everywhere.
+**Not the Hexagon** — see §11 — so the tablet runs it on its CPU. Work is
 scheduled in the `Background` class so a slider never waits on it (architecture §5.3).
 
 ## 8. Speed and the tablet
@@ -356,3 +367,57 @@ MIT architecture, so this model adds no third-party licence to D13.
 4. Whether a Lightroom or DxO comparison is available for §6.2.
 5. A borrowed X-Trans body, or X-Trans experimental in v1.
 
+## 11. What shipped in 0.21.0, and what was measured
+
+**Data.** 500 distinct ISO 50–100 6D frames from the library, over 121 shooting days (bursts and
+near-duplicate perceptual hashes dropped; 55 frames from held-out days for validation). Read through
+`dr-gpu`'s `mosaic_dump` example — `dr-decode` and the app's own hot-pixel pass — so the network's
+input is the mosaic the classical demosaic reads. Truth by 2×2 binning with a Catmull-Rom quarter-pixel
+shift of red and blue (§4.2). Training lives in `darkroom-denoise`, beside `darkroom-infill`.
+
+**Noise model (§5), from the library instead of a capture.** Shot gain and read variance per ISO from
+Adobe's `NoiseProfile` in the converted DNGs; read noise checked against each frame's masked border
+(agreement within 2–3 % from ISO 125 to 25600); read-noise *shape* taken from the border as quantiles
+on a tail-dense grid (excess kurtosis up to ~10 at high ISO), with only the photosites the app's
+hot-pixel rule would remove left out; row noise from the border's row means; **column noise** from
+the masked rows above the image — about a third of its variance is this sensor's fixed pattern.
+Third stops are their own rows: ISO 160, 320 and 640 are quieter than their neighbours, as §5.1
+expected. Training without the column noise left the 6D's vertical stripes in (0.90 DN of 1.01);
+with it, 0.17 DN.
+
+**Model.** Not NAFNet: its channel attention averages over the whole input, which breaks exact
+tiling. A U-Net of 3×3 convolutions, ReLU, strided and transposed convolutions and additive skips —
+3.2 M parameters, 48 GMAC per raw megapixel, receptive field 185 photosites (counted from the
+layers; a perturbation probe under-read it as 157 because a switched-off ReLU hides a path).
+Tiles of 1408 keep their central 1024 behind a 192 halo, exactly.
+
+**Results.** PSNR after the display transform, held-out days, step 60 000:
+
+| ISO | Network | Bilinear | Bilinear on a clean mosaic |
+|---|---|---|---|
+| 400 | 41.6 | 36.8 | 40.0 |
+| 1600 | 40.8 | 33.8 | 40.0 |
+| 6400 | 39.5 | 29.3 | 40.0 |
+| 25600 | 37.8 | 24.6 | 40.0 |
+
+Unbiased in linear light on real frames (shadow level within 1 % of a heavily averaged bilinear).
+Checked against the app's own render for channel and axis order (`tools/check_against_app.py`).
+
+**Precision (§8).** fp16: 0.00 dB at every ISO. int8 QDQ, calibrated on training tiles: −6 to −9 dB
+— the shadow steps §8 feared losing are lost. So the Hexagon refuses the role and the tablet runs f32
+on its CPU; the residual head of §8 is the route back.
+
+**Noise for any Bayer body (§3.3).** Table, then `NoiseProfile`, then the frame itself: read, row and
+column noise from its masked border, the shot gain alone estimated from the quietest flat patches.
+On 130 6D frames the estimate is within ±10 % of the table from ISO 1000 up and scattered below. The
+network loses under 0.3 dB for σ off by 15–20 % and twice as much for under- as for over-estimating;
+the estimate leans high. Every Bayer body is offered the switch; develop says which source was used.
+
+**Speed, a whole 6D frame (20 MP).** TensorRT fp16 3.1 s, ONNX Runtime CPU 14.4 s, on the laptop —
+measured while the GPU sat power-capped at an 810 MHz memory clock; uncapped is expected to be
+about four times faster. The Rust path reproduces the training repository's output to 2.5e-4 at
+worst; TensorRT fp16 is 75 dB from f32.
+
+**Not yet:** the result is not cached across sessions (§7.1) — reopening recomputes; the tripod real
+pairs of §6.1; X-Trans (§9); the hand-written WGSL path, for which `export.py` already writes the
+weights blob and a manifest a shader can follow.