{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:E7YY3HPCR2VK3GAEQH7YCZWTMG","short_pith_number":"pith:E7YY3HPC","canonical_record":{"source":{"id":"2505.23458","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T14:06:50Z","cross_cats_sorted":[],"title_canon_sha256":"5807fa1242d0f63dd464efb469d36b3d1af3b28642c0c3cf293d9d48ce5aa1c4","abstract_canon_sha256":"94250d12507002b66a24a31f6c9b7f30e1d3584a95f039310cf74efdbd5482e2"},"schema_version":"1.0"},"canonical_sha256":"27f18d9de28eaaad980481ff8166d361906e8dfbaa704a5c1a7cae289da77f59","source":{"kind":"arxiv","id":"2505.23458","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23458","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23458v1","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23458","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"pith_short_12","alias_value":"E7YY3HPCR2VK","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"pith_short_16","alias_value":"E7YY3HPCR2VK3GAE","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"pith_short_8","alias_value":"E7YY3HPC","created_at":"2026-07-05T11:12:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:E7YY3HPCR2VK3GAEQH7YCZWTMG","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23458","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T14:06:50Z","cross_cats_sorted":[],"title_canon_sha256":"5807fa1242d0f63dd464efb469d36b3d1af3b28642c0c3cf293d9d48ce5aa1c4","abstract_canon_sha256":"94250d12507002b66a24a31f6c9b7f30e1d3584a95f039310cf74efdbd5482e2"},"schema_version":"1.0"},"canonical_sha256":"27f18d9de28eaaad980481ff8166d361906e8dfbaa704a5c1a7cae289da77f59","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:02.134104Z","signature_b64":"nCr1THhBbzT08jEjasV9pWxYMixx1mBMX1NLXYKGiIe9wJHao0dMG2TutKuB1wkvs0PUDLwSRdRXSyANbgogDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27f18d9de28eaaad980481ff8166d361906e8dfbaa704a5c1a7cae289da77f59","last_reissued_at":"2026-07-05T11:12:02.133240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:02.133240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23458","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fRyEvSVLbzSDiVWckolWI0UiHZ02in8Tq0qOzYXM2Aonv1EeEyypMtM835tdCkb6fNeQaA2aX2YgRTHjRTf5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:04:43.441590Z"},"content_sha256":"33ed6fc370c85c66fff0ff478375443c05e12b44d7a1e2757e37b27c370dc129","schema_version":"1.0","event_id":"sha256:33ed6fc370c85c66fff0ff478375443c05e12b44d7a1e2757e37b27c370dc129"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:E7YY3HPCR2VK3GAEQH7YCZWTMG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diffusion Guidance Is a Controllable Policy Improvement Operator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kevin Frans, Pieter Abbeel, Seohong Park, Sergey Levine","submitted_at":"2025-05-29T14:06:50Z","abstract_excerpt":"At the core of reinforcement learning is the idea of learning beyond the performance in the data. However, scaling such systems has proven notoriously tricky. In contrast, techniques from generative modeling have proven remarkably scalable and are simple to train. In this work, we combine these strengths, by deriving a direct relation between policy improvement and guidance of diffusion models. The resulting framework, CFGRL, is trained with the simplicity of supervised learning, yet can further improve on the policies in the data. On offline RL tasks, we observe a reliable trend -- increased "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23458","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.23458/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6sQdHzgLRLSuy9oDE0TlftVHKYv/UmR/ovwiaOLt1I5yy+kSKOueimncR4D5RPtxc4vNQbW5q1GxV6SvbW7rBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:04:43.442070Z"},"content_sha256":"a79d5176a8fbc1888c49184f6f0fd462c2a5897b6d064f6661899cf3ccd09435","schema_version":"1.0","event_id":"sha256:a79d5176a8fbc1888c49184f6f0fd462c2a5897b6d064f6661899cf3ccd09435"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E7YY3HPCR2VK3GAEQH7YCZWTMG/bundle.json","state_url":"https://pith.science/pith/E7YY3HPCR2VK3GAEQH7YCZWTMG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E7YY3HPCR2VK3GAEQH7YCZWTMG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T10:04:43Z","links":{"resolver":"https://pith.science/pith/E7YY3HPCR2VK3GAEQH7YCZWTMG","bundle":"https://pith.science/pith/E7YY3HPCR2VK3GAEQH7YCZWTMG/bundle.json","state":"https://pith.science/pith/E7YY3HPCR2VK3GAEQH7YCZWTMG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E7YY3HPCR2VK3GAEQH7YCZWTMG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:E7YY3HPCR2VK3GAEQH7YCZWTMG","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":"94250d12507002b66a24a31f6c9b7f30e1d3584a95f039310cf74efdbd5482e2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T14:06:50Z","title_canon_sha256":"5807fa1242d0f63dd464efb469d36b3d1af3b28642c0c3cf293d9d48ce5aa1c4"},"schema_version":"1.0","source":{"id":"2505.23458","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23458","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23458v1","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23458","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"pith_short_12","alias_value":"E7YY3HPCR2VK","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"pith_short_16","alias_value":"E7YY3HPCR2VK3GAE","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"pith_short_8","alias_value":"E7YY3HPC","created_at":"2026-07-05T11:12:02Z"}],"graph_snapshots":[{"event_id":"sha256:a79d5176a8fbc1888c49184f6f0fd462c2a5897b6d064f6661899cf3ccd09435","target":"graph","created_at":"2026-07-05T11:12:02Z","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/2505.23458/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"At the core of reinforcement learning is the idea of learning beyond the performance in the data. However, scaling such systems has proven notoriously tricky. In contrast, techniques from generative modeling have proven remarkably scalable and are simple to train. In this work, we combine these strengths, by deriving a direct relation between policy improvement and guidance of diffusion models. The resulting framework, CFGRL, is trained with the simplicity of supervised learning, yet can further improve on the policies in the data. On offline RL tasks, we observe a reliable trend -- increased ","authors_text":"Kevin Frans, Pieter Abbeel, Seohong Park, Sergey Levine","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T14:06:50Z","title":"Diffusion Guidance Is a Controllable Policy Improvement Operator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23458","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":"sha256:33ed6fc370c85c66fff0ff478375443c05e12b44d7a1e2757e37b27c370dc129","target":"record","created_at":"2026-07-05T11:12:02Z","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":"94250d12507002b66a24a31f6c9b7f30e1d3584a95f039310cf74efdbd5482e2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T14:06:50Z","title_canon_sha256":"5807fa1242d0f63dd464efb469d36b3d1af3b28642c0c3cf293d9d48ce5aa1c4"},"schema_version":"1.0","source":{"id":"2505.23458","kind":"arxiv","version":1}},"canonical_sha256":"27f18d9de28eaaad980481ff8166d361906e8dfbaa704a5c1a7cae289da77f59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27f18d9de28eaaad980481ff8166d361906e8dfbaa704a5c1a7cae289da77f59","first_computed_at":"2026-07-05T11:12:02.133240Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:02.133240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nCr1THhBbzT08jEjasV9pWxYMixx1mBMX1NLXYKGiIe9wJHao0dMG2TutKuB1wkvs0PUDLwSRdRXSyANbgogDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:02.134104Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23458","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33ed6fc370c85c66fff0ff478375443c05e12b44d7a1e2757e37b27c370dc129","sha256:a79d5176a8fbc1888c49184f6f0fd462c2a5897b6d064f6661899cf3ccd09435"],"state_sha256":"d4e00dc4503ba6ea9d6848e2209852d4465e63bd44dee92822729af0f6997c98"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S3IA9U92DSfisp3Y3zeQVpZIgDN+6qQRom1B1RiiUAdmwTd0dyAYcib6ardz6G6fYGh1NiZUUPP6Jyd+0aK0Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:04:43.446268Z","bundle_sha256":"6bf1b46503b1f753f1e651eb0679d16ca4734ab248a2f173071b482bc317c3e9"}}