Trajectory Phase Labeling

Each trajectory chunk is assigned to one of five semantic phases — active-grip, pre-grasp, release-ramp, approach, and tail — using a deterministic gripper-state-based heuristic. Active-grip and pre-grasp phases consistently dominate PCM's chunk allocation throughout training because they carry the highest success-failure action variance. Tail-phase chunks are assigned only floor-probability selection because they represent downstream consequences of failure rather than causally critical moments. Phase labels are applied identically to successful and failed trajectories to ensure per-phase comparisons are like-for-like. Gripper-state phase labeling is specific to single-gripper manipulation and has not been empirically validated for dexterous hands or locomotion settings.