Update model card

README.md

@@ -48,13 +48,9 @@ sRGB gamma — DDColor is trained against `cv2.cvtColor` float Lab):
 4. Resize ab back to the original size, concatenate with the **original-resolution
    L**, and convert Lab→RGB. Only chroma is low-res; full-res luminance is preserved.
 
-A reference JavaScript implementation of exactly this pipeline lives in the
-`ddcolor.mjs` factory of the Edge Tools build (see Provenance).
-
 ## Provenance
 
-Reproducibly built in CI from the upstream PyTorch checkpoint — nothing here is
-hand-massaged:
+Exported from the upstream PyTorch checkpoint — reproducible from public sources:
 
 - **Architecture code**: [`piddnad/DDColor`](https://github.com/piddnad/DDColor)
   pinned at `2adb63f2656ac41cbdf7b894cddd94121a3faf13`
@@ -68,8 +64,9 @@ hand-massaged:
   cast to float16 via `onnxconverter_common.float16.convert_float_to_float16(
   ..., keep_io_types=True)`. `onnxsim` / symbolic-shape-infer are skipped — the
   input is fixed-size, so shapes are already static.
-- **Built & published by**: the `edge-tools/wasm/ddcolor` CI project, which also
-  runs a colorization test against this exact artifact before publishing it.
+- **Validation**: every published build is checked by an automated colorization
+  test against this exact artifact before upload — a grayscale input must come
+  back with real chroma while preserving the source luminance.
 
 ## License