{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SI3M65ELF4MCZ5KA43M7O3TION","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ca8df28d4a73c6214a275a32f4be489428ee5f87e2a3023562a3c88c6c45b443","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T18:06:04Z","title_canon_sha256":"5cc51eca7b61b70fecff8a8d1ec97624ad1ba8faab38975ee36d993751af1a71"},"schema_version":"1.0","source":{"id":"2606.13795","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.13795","created_at":"2026-06-19T16:12:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.13795v2","created_at":"2026-06-19T16:12:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13795","created_at":"2026-06-19T16:12:06Z"},{"alias_kind":"pith_short_12","alias_value":"SI3M65ELF4MC","created_at":"2026-06-19T16:12:06Z"},{"alias_kind":"pith_short_16","alias_value":"SI3M65ELF4MCZ5KA","created_at":"2026-06-19T16:12:06Z"},{"alias_kind":"pith_short_8","alias_value":"SI3M65EL","created_at":"2026-06-19T16:12:06Z"}],"graph_snapshots":[{"event_id":"sha256:83a915e6da02ca893f4e62b400e154b1144a4ef411989a21d9e9e4f553514266","target":"graph","created_at":"2026-06-19T16:12:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.13795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"RL post-training has become increasingly pivotal for improving diffusion policies, but existing diffusion policy-gradient methods are often unstable and cannot achieve reliable policy improvement. We identify the cause as the double-drift phenomenon: optimizing a variational surrogate can let the ELBO separate from the true log-likelihood, which then makes the resulting proxy policy gradient misaligned with the true policy gradient of expected return. We propose \\textbf{DiPOD}, a diffusion policy optimization framework that maintains tight-bound behavior throughout training by interleaving sel","authors_text":"Angjoo Kanazawa, Haiwen Feng, Haozhe Jiang, Jiantao Jiao, Nika Haghtalab, Pieter Abbeel","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T18:06:04Z","title":"DiPOD: Diffusion Policy Optimization without Drifting Apart"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13795","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1436c1031e01fde8743459e6c345b4b6cfb41ad33535781e99a902f7f1797e24","target":"record","created_at":"2026-06-19T16:12:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ca8df28d4a73c6214a275a32f4be489428ee5f87e2a3023562a3c88c6c45b443","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T18:06:04Z","title_canon_sha256":"5cc51eca7b61b70fecff8a8d1ec97624ad1ba8faab38975ee36d993751af1a71"},"schema_version":"1.0","source":{"id":"2606.13795","kind":"arxiv","version":2}},"canonical_sha256":"9236cf748b2f182cf540e6d9f76e687348792d370ebbfd30d7cad8cc8685d51f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9236cf748b2f182cf540e6d9f76e687348792d370ebbfd30d7cad8cc8685d51f","first_computed_at":"2026-06-19T16:12:06.521130Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:06.521130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"flTGEjq+fMaUQFoZY+xwz4t61XIEZWaVgl2GDkb6L0GxAkFhYzzmtyw6bCdHBzp34pzhXmzuoQBvA4CsDqdbAQ==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:06.521540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.13795","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1436c1031e01fde8743459e6c345b4b6cfb41ad33535781e99a902f7f1797e24","sha256:83a915e6da02ca893f4e62b400e154b1144a4ef411989a21d9e9e4f553514266"],"state_sha256":"bec49e9b082c6ca960f49f11bb3c82cd44be63df0229f146a86f9f7343c72537"}