Loading...
Loading...
Contributors:
Dataset URI:
10.5281/zenodo.23442248Data, code and protocol for a statistical audit of real-robot evaluations in 89 arXiv papers (posted January–September 2026) on force-, torque-, tactile- and motor-current-aware robot manipulation. The archive includes: the pre-specified protocol with timestamped deviations D1–D9; per-paper extraction records with sources; the blinded second extraction (by separate AI-assistant instances), with comparison and adjudication logs; the analysis code (Wilson and Newcombe intervals, Fisher and Boschloo tests, Holm correction, exact Fisher power, null simulation, sequential test) with unit tests; generated results, figures and LaTeX source; the blinded human re-check sheets (in progress) and author-confirmation sheets. The full git history is included, so the protocol timestamps can be checked. Run python3 analyze.py, then make_figures.py and make_tables.py, to reproduce every number in the paper.
Keyword(s):
evaluation methodology; force control; meta-research; reproducibility; robot manipulation.
MeSH Term(s):
Grants and Funding:
No Grants or Funding Data Available
Associated Publication(s):
No Associated Publication Data Available
Supplementary Data:
No Supplementary Data Available
Related Dataset(s):
No Related Dataset Data Available
The National Library of Medicine (NLM) provides information about biomedical datasets. Inclusion on an NLM Web page does not imply endorsement of, or agreement with, the contents by NLM or the National Institutes of Health. Learn more: NLM Web Policies (nih.gov)