{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PLSN4G3AY2R3LTTGDUX3Y5YEGG","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":"8145822fecc2c1f67c4539cef3a4841c0353159f2704c009aaad322bf249bf3f","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-09T14:46:48Z","title_canon_sha256":"67a3a9f9564ce404ac12db6471e2ae1cadebf183f80d3ee7d17dd30a43b64e01"},"schema_version":"1.0","source":{"id":"2404.06356","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06356","created_at":"2026-07-05T08:06:08Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06356v1","created_at":"2026-07-05T08:06:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06356","created_at":"2026-07-05T08:06:08Z"},{"alias_kind":"pith_short_12","alias_value":"PLSN4G3AY2R3","created_at":"2026-07-05T08:06:08Z"},{"alias_kind":"pith_short_16","alias_value":"PLSN4G3AY2R3LTTG","created_at":"2026-07-05T08:06:08Z"},{"alias_kind":"pith_short_8","alias_value":"PLSN4G3A","created_at":"2026-07-05T08:06:08Z"}],"graph_snapshots":[{"event_id":"sha256:91e92e0a049322825c7cf8b610caed423b1d00b1a83e32322d10a76745aa7cb3","target":"graph","created_at":"2026-07-05T08:06:08Z","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/2404.06356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many real-world settings, agents must learn from an offline dataset gathered by some prior behavior policy. Such a setting naturally leads to distribution shift between the behavior policy and the target policy being trained - requiring policy conservatism to avoid instability and overestimation bias. Autoregressive world models offer a different solution to this by generating synthetic, on-policy experience. However, in practice, model rollouts must be severely truncated to avoid compounding error. As an alternative, we propose policy-guided diffusion. Our method uses diffusion models to g","authors_text":"Benjamin Ellis, Cong Lu, Jakob Foerster, Matthew Thomas Jackson, Michael Tryfan Matthews, Shimon Whiteson","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-09T14:46:48Z","title":"Policy-Guided Diffusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06356","kind":"arxiv","version":1},"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:c57e8981652ab32db5766e077b896c14ff601b5fc817d569d39f9c6dafbde26a","target":"record","created_at":"2026-07-05T08:06:08Z","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":"8145822fecc2c1f67c4539cef3a4841c0353159f2704c009aaad322bf249bf3f","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-09T14:46:48Z","title_canon_sha256":"67a3a9f9564ce404ac12db6471e2ae1cadebf183f80d3ee7d17dd30a43b64e01"},"schema_version":"1.0","source":{"id":"2404.06356","kind":"arxiv","version":1}},"canonical_sha256":"7ae4de1b60c6a3b5ce661d2fbc77043187d17a8d96e8dd5c7d981a07bf1fb536","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ae4de1b60c6a3b5ce661d2fbc77043187d17a8d96e8dd5c7d981a07bf1fb536","first_computed_at":"2026-07-05T08:06:08.077019Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:08.077019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wHEuqJ/KoWZDzOV95cXt7SgJLnOEBE9zSAftWPsVZkEoGjb5wNcg/Dg4FPV5kA3H2VqotsxJCUbO9id7bsZnDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:08.077511Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.06356","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c57e8981652ab32db5766e077b896c14ff601b5fc817d569d39f9c6dafbde26a","sha256:91e92e0a049322825c7cf8b610caed423b1d00b1a83e32322d10a76745aa7cb3"],"state_sha256":"d23947f27801a06d4885eb1fade6be1f150b9983d34791cf4b9255af61c24a3e"}