Repository navigation
Publish shoe graspability diagnostic and full native evidence - #40
Merged
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The earlier shoe study could not distinguish difficult geometry from the modeled gripper and attached tool. Publish a frozen direct-grasp diagnostic with three rigid shapes, two loads, two layout/friction combinations and mounted/absent rake conditions.
All 24 attempts are valid: the 30 g controls retain 8/12 lifts; every 300 g condition fails, including the block. Removing the rake gains one narrow-shoe result and loses one block result. Both retained current-shoe cases exceed nominal jaw travel under compliant simulator limits, which is disclosed separately from the unchanged retention scores.
Includes the unchanged 107-file native replay export, every full contact trace, source-bound independent audit, recorded jaw-limit diagnostic, root acceptance and honest reproduction/licensing notes. Adds research navigation and a scoped gzip mirror for the new Hugging Face release; earlier paper bodies and evidence remain unchanged.
Validation: build and link validation passed; 63 research tests passed. Independent audit verifies all 24 models/attempts without stepping physics. Root local browser QA loaded/scrubbed all 24 replays, matched eight displayed lifts, and reported no console errors/warnings. This is authored direct pickup with synthetic objects, not a learned shoe skill or physical hardware qualification.