I built a leakage-clean verifier for robot manipulation, is this useful? Am I solving a non-problem? [D]

Spent the last few weeks on a benchmark/harness that tries to answer one question honestly: did a robot arm actually do the demonstrated task, or did the success metric just get fooled? The setup: compile a human demo into an object-centric graph (what changed in the world: relations, contacts, event order), run a solver, then independently extract a graph from the rollout only and check if they match. The whole point is a hard information boundary so the "answer key" can never leak into the side that grade