Overview/Cases
Simulated data
Cases
Each case is one sealed evidence package. The stress tests deliberately break clock sync, shift the facility clock by 1.8 s, or remove a source, to show how Kinwit behaves when the evidence is weak.
| Case | Incident | Sources | Integrity | Cross-source order | |
|---|---|---|---|---|---|
| SIM-2026-0001 Flagship | Facility-triggered safety stop The facility stop broadcast (E-004) precedes the robot's recorded stop input (E-005) by 11.754 to 17.976 ms on the aligned timeline. | 2/2 | Verified | Proven | Open → |
| SIM-2026-0002 Stress test | Safety stop with congested clock sync (ordering ambiguity test) The order of the facility stop broadcast (E-004) and the robot stop input (E-005) cannot be determined: the delta interval [-11.954, 21.046]… | 2/2 | Verified | Not provable | Open → |
| SIM-2026-0003 Stress test | Safety stop with a 1.8 s facility clock error (alignment robustness test) The facility stop broadcast (E-004) precedes the robot's recorded stop input (E-005) by 11.754 to 17.976 ms on the aligned timeline. | 2/2 | Verified | Proven | Open → |
| SIM-2026-0004 Stress test | Safety stop with facility source missing (incomplete evidence test) E-003 Robot safety I/O registers external stop input → E-006 Zero velocity command recorded on /cmd_vel → E-007 Odometry reports speed < 0.0… | 1/2 | Verified | No cross-check | Open → |