Observed arrival · 2026-08-29
Orbit Ship-Gate Measures Whether a Robot Policy Really Improved
Orbit is deployment infrastructure that measures training variance in robot-policy evaluations and turns it into promotion, acceptance, and certificate decisions.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
Field notes
The product is organized around a noise-floor measurement rather than a single benchmark score. Its displayed examples separate suite-level variance from per-task variance, including a LIBERO object result of 11.00 percentage points versus 4.23 for the suite. A sample GitHub Actions invocation compares incumbent and candidate runs and records a verdict, corrected delta, required retrain count, and ledger hash.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
⊠LoginAccess appeared gated
$PaidCommerce or pricing visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue