{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BVLK2X3UQM32IPFI2QGRZDGMHT","short_pith_number":"pith:BVLK2X3U","canonical_record":{"source":{"id":"2309.06599","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-12T20:58:21Z","cross_cats_sorted":[],"title_canon_sha256":"49ac730a4114f39bdeef93ed4e1fd5a981d1f0fb34918144d52d52097f0f7851","abstract_canon_sha256":"ce42bb9a959a503612e4cb33bb23381bf5715c95073e0394b0c423d7c89dc612"},"schema_version":"1.0"},"canonical_sha256":"0d56ad5f748337a43ca8d40d1c8ccc3cdf3deaed8aea04bb3dcf0243bca0a771","source":{"kind":"arxiv","id":"2309.06599","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.06599","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"arxiv_version","alias_value":"2309.06599v1","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06599","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"pith_short_12","alias_value":"BVLK2X3UQM32","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"pith_short_16","alias_value":"BVLK2X3UQM32IPFI","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"pith_short_8","alias_value":"BVLK2X3U","created_at":"2026-07-05T06:50:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BVLK2X3UQM32IPFI2QGRZDGMHT","target":"record","payload":{"canonical_record":{"source":{"id":"2309.06599","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-12T20:58:21Z","cross_cats_sorted":[],"title_canon_sha256":"49ac730a4114f39bdeef93ed4e1fd5a981d1f0fb34918144d52d52097f0f7851","abstract_canon_sha256":"ce42bb9a959a503612e4cb33bb23381bf5715c95073e0394b0c423d7c89dc612"},"schema_version":"1.0"},"canonical_sha256":"0d56ad5f748337a43ca8d40d1c8ccc3cdf3deaed8aea04bb3dcf0243bca0a771","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:20.138865Z","signature_b64":"kgJ10XMJ7b5rRgAPLsY3kWniGuHUVKaB7LAmWun4n5ZBxj/82r8ROFKqot9yUvJ0K8zBGFceHtXI2izL+FhcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d56ad5f748337a43ca8d40d1c8ccc3cdf3deaed8aea04bb3dcf0243bca0a771","last_reissued_at":"2026-07-05T06:50:20.138403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:20.138403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.06599","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":"2026-07-05T06:50:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+WZXhIkkPcEMJ9gqVxSr9j+4cPj60pn1taj0wapn9Dr49gFK+4VQKLm0AyXi1OuS1VqcrrpeGIFBJcyiVJs5DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:41:40.856737Z"},"content_sha256":"77f3b9d409e8507e44d35219790e046090cc72011814bc53a907942dc1a346c1","schema_version":"1.0","event_id":"sha256:77f3b9d409e8507e44d35219790e046090cc72011814bc53a907942dc1a346c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BVLK2X3UQM32IPFI2QGRZDGMHT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reasoning with Latent Diffusion in Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Glen Berseth, Jeff Schneider, John Dolan, Ravi Tej Akella, Shivesh Khaitan, Siddarth Venkatraman","submitted_at":"2023-09-12T20:58:21Z","abstract_excerpt":"Offline reinforcement learning (RL) holds promise as a means to learn high-reward policies from a static dataset, without the need for further environment interactions. However, a key challenge in offline RL lies in effectively stitching portions of suboptimal trajectories from the static dataset while avoiding extrapolation errors arising due to a lack of support in the dataset. Existing approaches use conservative methods that are tricky to tune and struggle with multi-modal data (as we show) or rely on noisy Monte Carlo return-to-go samples for reward conditioning. In this work, we propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06599","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/2309.06599/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":"2026-07-05T06:50:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tbQOZjmer0tPMslQNqLynnBA5pRwW85Dcl6GcmE8CSr5Hs31UR0G/yYb471BWq7OAhIC6edB6WNEfQPAf8NFAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:41:40.857584Z"},"content_sha256":"f9e991d9ef543b1ecab14fdd3aef6d115736d6e130d531afd0bca7d2d9e888cd","schema_version":"1.0","event_id":"sha256:f9e991d9ef543b1ecab14fdd3aef6d115736d6e130d531afd0bca7d2d9e888cd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BVLK2X3UQM32IPFI2QGRZDGMHT/bundle.json","state_url":"https://pith.science/pith/BVLK2X3UQM32IPFI2QGRZDGMHT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BVLK2X3UQM32IPFI2QGRZDGMHT/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":"2026-08-04T15:41:40Z","links":{"resolver":"https://pith.science/pith/BVLK2X3UQM32IPFI2QGRZDGMHT","bundle":"https://pith.science/pith/BVLK2X3UQM32IPFI2QGRZDGMHT/bundle.json","state":"https://pith.science/pith/BVLK2X3UQM32IPFI2QGRZDGMHT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BVLK2X3UQM32IPFI2QGRZDGMHT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BVLK2X3UQM32IPFI2QGRZDGMHT","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":"ce42bb9a959a503612e4cb33bb23381bf5715c95073e0394b0c423d7c89dc612","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-12T20:58:21Z","title_canon_sha256":"49ac730a4114f39bdeef93ed4e1fd5a981d1f0fb34918144d52d52097f0f7851"},"schema_version":"1.0","source":{"id":"2309.06599","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.06599","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"arxiv_version","alias_value":"2309.06599v1","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06599","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"pith_short_12","alias_value":"BVLK2X3UQM32","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"pith_short_16","alias_value":"BVLK2X3UQM32IPFI","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"pith_short_8","alias_value":"BVLK2X3U","created_at":"2026-07-05T06:50:20Z"}],"graph_snapshots":[{"event_id":"sha256:f9e991d9ef543b1ecab14fdd3aef6d115736d6e130d531afd0bca7d2d9e888cd","target":"graph","created_at":"2026-07-05T06:50:20Z","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/2309.06599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) holds promise as a means to learn high-reward policies from a static dataset, without the need for further environment interactions. However, a key challenge in offline RL lies in effectively stitching portions of suboptimal trajectories from the static dataset while avoiding extrapolation errors arising due to a lack of support in the dataset. Existing approaches use conservative methods that are tricky to tune and struggle with multi-modal data (as we show) or rely on noisy Monte Carlo return-to-go samples for reward conditioning. In this work, we propose ","authors_text":"Glen Berseth, Jeff Schneider, John Dolan, Ravi Tej Akella, Shivesh Khaitan, Siddarth Venkatraman","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-12T20:58:21Z","title":"Reasoning with Latent Diffusion in Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06599","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":"sha256:77f3b9d409e8507e44d35219790e046090cc72011814bc53a907942dc1a346c1","target":"record","created_at":"2026-07-05T06:50:20Z","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":"ce42bb9a959a503612e4cb33bb23381bf5715c95073e0394b0c423d7c89dc612","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-12T20:58:21Z","title_canon_sha256":"49ac730a4114f39bdeef93ed4e1fd5a981d1f0fb34918144d52d52097f0f7851"},"schema_version":"1.0","source":{"id":"2309.06599","kind":"arxiv","version":1}},"canonical_sha256":"0d56ad5f748337a43ca8d40d1c8ccc3cdf3deaed8aea04bb3dcf0243bca0a771","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d56ad5f748337a43ca8d40d1c8ccc3cdf3deaed8aea04bb3dcf0243bca0a771","first_computed_at":"2026-07-05T06:50:20.138403Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:50:20.138403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kgJ10XMJ7b5rRgAPLsY3kWniGuHUVKaB7LAmWun4n5ZBxj/82r8ROFKqot9yUvJ0K8zBGFceHtXI2izL+FhcBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:50:20.138865Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.06599","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77f3b9d409e8507e44d35219790e046090cc72011814bc53a907942dc1a346c1","sha256:f9e991d9ef543b1ecab14fdd3aef6d115736d6e130d531afd0bca7d2d9e888cd"],"state_sha256":"469d2da46f665da7cb0277157d49e40138a75c15387828e90fbca761e116f212"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UXiE0hHUafA+vRgr7ip2jtRfFLhgqPoMRVLgfC2vcfNwlJt0o08VaCYmSj8H2hmMNkxiDzliSL+X5Heu+bGGAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T15:41:40.861208Z","bundle_sha256":"889a37dc34f29433ed3d7532fef0d2a94ea00d8dd673917a4c064c366b4b30aa"}}