Repository navigation
Publish PiPER v0.5 placement reliability and complete evidence - #30
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 v0.5 comparison: the revised grasp completes 23/36 placements versus 15/36 for v0.4 and 18/36 with second-lift recovery alone. It gains eight completions and loses none across three fresh cohorts, while the fifteen shared successes average 0.772 simulated seconds slower. Twelve low-friction acquisition failures and one later retention failure remain.
Adds the research paper, publication catalog and homepage entry, a v0.4 follow-up link, and all 270 original receipt files covering 252 valid attempts and 144 failed negative controls. The article preserves the force and timing tradeoffs, including 1,035 software windows above 20 ms, and separates the 200-attempt development archive from fresh confirmation. Authored simulator control remains distinct from learned skills, calibrated contact physics and physical hardware qualification. Runtime and results are linked to immutable GitHub commits; the Hugging Face publication is linked to its verified immutable revision.
Validation: all 51 research tests pass, including complete sealed-attempt and paired-control checks, all computation windows, immutable publication links, license/identity scope, deterministic output and local link resolution.
npm run checkpasses: 19 publications, 4 topic readers and 988 public artifacts build successfully; topic metadata, bibliography keys, local links and cover images validate. The Hugging Face receipt records readback verification of all 563 payload files. A separate GitHub snapshot records 28 passing push/PR checks for training code/results head0545ac4; later publication-only commits require their own checks.Local browser checks pass at desktop, 390px and 320px widths with no page overflow or JavaScript errors and all three cohort-report links present. The dedicated Cloudflare Worker deployment dry-run passes.
The research article is live. All 312 added/changed public site files match the tested local bytes, including all 270 sealed native evidence files. Live research and Hugging Face pages pass desktop, 390px and 320px browser checks with no page overflow or JavaScript errors. All 28 checks on final training head 05d267f also pass.