Repository navigation
Conversation
This was referenced Oct 13, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add two native PiPER experiments for skill prerequisites: a passive shoe-box lid with withdrawal and resumption, and a pre-mounted rake that brings a free shoe into the controller workspace before a separate retained-lift check. Both preserve native contacts, bounded actuator commands, complete failure receipts and a branded 3D replay.
Frozen source:
756306a2beda60ac54567971626080a56227e781. The single held-out run retains all 16 attempts: the lid guard avoids both baseline collisions while completing 2/4 tasks; the rake retrieves 3/4 shoes but completes 0/4 retained lifts. The closed-box and unsuitable-tool cases remain unfinished. These are authored policies with simulator observations and synthetic mechanics, not learned or hardware-validated skills. The browser replays native results; CPU commands reproduce the simulation.Validation: 19 native/evidence tests, 13 publication tests, reproducible pinned viewer build, and desktop plus 390/320px browser checks. CI repeats development cases only. The new versioned export preserves historical Hugging Face and research artifacts. This PR is stacked on #17 to isolate the new work.