Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Scope
Fixes the MLWM alpha1 desktop/runtime neural path.
Root Cause
The alpha1 model was trained and promoted without a classical frequency-domain sync template, but the runtime embed path still injected that template before decode. That changed the image distribution enough for forced neural extraction to fail on a clean self-check.
Changes
Validation
python -m unittest discover -s blind_watermark\\testsnpm run typecheck.venv-mlneural ONNX smoke test: embed/extractALPHA1-42, confidence ~0.998,engineUsed=neuralRollback
Revert this commit to restore the previous sync-template runtime behavior, though that is expected to break alpha1 forced-neural extraction until a future model is trained with sync augmentation.