Repository navigation
Publish PiPER contact history v0.3 and all 84 simulation attempts - #28
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Publish the frozen PiPER contact-history v0.3 comparison: history completes 6/12 placements versus 4/12 for both original and probe-only motion. All 84 native attempts are valid and all 48 negative controls remain unsuccessful. The two added completions are 60 g nominal-friction blocks; easier cases incur extra task time, and all six history acquisition retries still fail.
The paper and research homepage expose the complete original 90-file receipt, the frozen source, separate 13-attempt development archive, execution timing boundary and immutable Hugging Face evidence. Actual movement after requested slowdown/hold remains visible, including two intervals that initially accelerate, five resumes across four completed tasks, and one resume failing the independent low absolute-motion check. No physical sensing, learned policy or hardware qualification is claimed.
Validation covers all stored and decoded hashes, the full paired denominator, source/native model identity, exact matched open-jaw command tapes, causal recorded history and task outcomes. Runtime timing consists of per-attempt summaries, maxima and miss counts; raw per-decision wall-time samples are not retained.
Training code and evidence PR · Hugging Face original bundle
Validation: npm run check passed; all 46 research tests passed. The site includes 17 papers and 605 public artifacts.