Reviewed relationships 1
Verified
GraspVLA Model trained on SynGrasp-1B
Scope synthetic pretraining
Boundary The source states one billion synthetic VLA frames; frames are not trajectories or hours.
Canonical evidence claims 12
Claims are projected from authored tables. A dash remains an explicit missing value; it is never filled from a neighboring product or name match.
Robotics benchmarks — suite identity, not a ranking Robot Training Corpus 12 rows · 2 declared gaps
| Metric | Value and evidence |
|---|---|
| Claim boundary | frames are not hours or trajectories. Not DexGraspNet’s 1.32 million grasps [R17] |
| Embodiment in the source | synthetic grasping VLA frames; not a named robot SKU [R17] |
| Engine / renderer | Declared gap |
| First public date | arXiv 2025-05-06 [R17] |
| Kind | synthetic VLA pretraining frames used with GraspVLA [R17] |
| Language-conditioned | synthetic VLA frames with action data in the paper [R17] |
| Medium | synthetic [R17] |
| Paper | arXiv:2505.03233 [R17] |
| Primary metric family | pretraining frames for GraspVLA [R17] |
| Public code | promised with GraspVLA; check the project page for release [R17] |
| Public leaderboard | Declared gap |
| Published scale | 1 billion synthetic VLA frames [R17] |
Source ledger 1
What is not inferred
No fuzzy entity matching, adjacent-column borrowing, universal compatibility, commercial maturity, or checkpoint-to-product identity. Absence of a relation means unreviewed or unsupported here—not proven incompatibility.