BELIEF BEYOND VISIBILITY: GROUNDING, UPDATING, AND PRESERVING PHYSICAL STATE FOR MANIPULATION

Complex, long-horizon manipulation requires robots to update their estimates when interactions change an object's state and retain supported information when objects become hidden and viewpoints shift. Memory-augmented policies exploit interaction histories, while persistent scene models retain objects and relations across observations. However, task success and average attribute accuracy do not reveal when, after a transition, the system jointly recovers the required physical attributes of the correct task object. We formulate task-conditioned structured belief maintenance, including causal estimation of object existence, visibility, object–container relations, spatial evidence, and container articulation, with physical state separated from task roles. We introduce CERB (Control-Evidence-Routed Belief), which combines a learned multi-view object-centric observer with action-conditioned temporal inference and measurement-based belief revision. In CERB, state candidates are inferred from visual history, executed actions, and proprioceptive feedback, corrected by accumulated observation evidence, and integrated with the previously accepted belief by a learned update. Thus, new evidence can rectify an erroneous estimate without requiring a physical transition. To evaluate these capabilities, we introduce Primary35, a 35-task, three-view benchmark whose event-aligned criteria require applicable task binding and physical fields to recover together. Across three training repetitions, under the same frozen observer and complete output interface, CERB improves actionable recovery from $38.9\%$ to $59.6\%$ and complete-object recovery from $43.0\%$ to $45.3\%$ over the strongest adapted temporal baseline on in-distribution episodes held out from temporal training. The actionable-recovery gain persists when target-object assets are held out from temporal training.