Bounded-Fidelity Sim-as-Demo-Stage: Mocap Handoff for Governance Benchmarks

What happened

arXiv:2610.00008v1 Announce Type: new Abstract: Sim-to-real research pursues physics fidelity as a primary objective: simulators are judged by how closely they reproduce real-world contact dynamics. For governance benchmarking of LLM-driven robots, where the simulator demonstrates that an admission/policy/contract/audit pipeline behaves correctly, contact fidelity at object handoffs (grasp, carry, place) becomes a liability: contact-force integration noise injects audit-chain divergence that is structurally unrelated to the governance property under test.

The construction operates with MuJoCo's mocap-body primitive driven by a 220-line Python adapter that the governance bridge invokes via structured intents. Across N=1000 replays per posture, the mocap variant produces one distinct audit-chain hash (1000/1000 byte-identical; Wilson 95% CI [0.997, 1.000]); the contact-force baseline produces 584 distinct hashes (993/1000 diverged; CI [0.987, 0.998]).

Key facts

• The construction — uses: MuJoCo's mocap-body primitive driven by a 220-line Python adapter that the governance bridge invokes via structured intents