{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KPSUWKPRIT472FD2HPZOIJUJQA","short_pith_number":"pith:KPSUWKPR","canonical_record":{"source":{"id":"2405.16173","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T10:45:46Z","cross_cats_sorted":[],"title_canon_sha256":"66fbafec92d898a874dda4f6a5789ddfdb905e68ee073875b096cc7a31c0f9a3","abstract_canon_sha256":"d30d10b728f02345bd2b276d2b19e89ea919d419df38d74a6cc3a4b446445e5b"},"schema_version":"1.0"},"canonical_sha256":"53e54b29f144f9fd147a3bf2e4268980070edb3ac08fdd1707af79b6fecf1c06","source":{"kind":"arxiv","id":"2405.16173","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16173","created_at":"2026-07-05T09:49:42Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16173v3","created_at":"2026-07-05T09:49:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16173","created_at":"2026-07-05T09:49:42Z"},{"alias_kind":"pith_short_12","alias_value":"KPSUWKPRIT47","created_at":"2026-07-05T09:49:42Z"},{"alias_kind":"pith_short_16","alias_value":"KPSUWKPRIT472FD2","created_at":"2026-07-05T09:49:42Z"},{"alias_kind":"pith_short_8","alias_value":"KPSUWKPR","created_at":"2026-07-05T09:49:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KPSUWKPRIT472FD2HPZOIJUJQA","target":"record","payload":{"canonical_record":{"source":{"id":"2405.16173","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T10:45:46Z","cross_cats_sorted":[],"title_canon_sha256":"66fbafec92d898a874dda4f6a5789ddfdb905e68ee073875b096cc7a31c0f9a3","abstract_canon_sha256":"d30d10b728f02345bd2b276d2b19e89ea919d419df38d74a6cc3a4b446445e5b"},"schema_version":"1.0"},"canonical_sha256":"53e54b29f144f9fd147a3bf2e4268980070edb3ac08fdd1707af79b6fecf1c06","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:42.842180Z","signature_b64":"cbLX8EESnAJQ/1aMVT2arlZSAVpfzfuHNzVRnU6JJhYbLqC61KF9/rzFiSrL8zEYppIy3A8uLZh3F84FN1zzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53e54b29f144f9fd147a3bf2e4268980070edb3ac08fdd1707af79b6fecf1c06","last_reissued_at":"2026-07-05T09:49:42.841696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:42.841696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.16173","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:49:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uzxWe7ToHrrXvk88i+Qt+LOD5ur/Kq1q03qqBQp68U/nhE1QimQ//9VLDAQIukLvE/BRb1fpkf6ATlAlsgPZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:54:26.894152Z"},"content_sha256":"86d2eb205c54263fe80849d401436613008dcaaeeed2f42e55978811a6488341","schema_version":"1.0","event_id":"sha256:86d2eb205c54263fe80849d401436613008dcaaeeed2f42e55978811a6488341"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KPSUWKPRIT472FD2HPZOIJUJQA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jingya Wang, Jingyi Yu, Kan Ren, Ke Hu, Shutong Ding, Weinan Zhang, Ye Shi, Zhenhao Zhang","submitted_at":"2024-05-25T10:45:46Z","abstract_excerpt":"Diffusion models have garnered widespread attention in Reinforcement Learning (RL) for their powerful expressiveness and multimodality. It has been verified that utilizing diffusion policies can significantly improve the performance of RL algorithms in continuous control tasks by overcoming the limitations of unimodal policies, such as Gaussian policies, and providing the agent with enhanced exploration capabilities. However, existing works mainly focus on the application of diffusion policies in offline RL, while their incorporation into online RL is less investigated. The training objective "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16173","kind":"arxiv","version":3},"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/2405.16173/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":"2026-07-05T09:49:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6/XimgOUhr/C1h+zXiV6TDq9OcpNv+r131rWI2BZ3UDj7IvoICS5RZ8EYSie0183LVsRwPtaHUfptBcbPB3+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:54:26.894646Z"},"content_sha256":"a646ce392176477bef8b6a704133b0bded590dd9a69c7929fcffaa4f3a8d0711","schema_version":"1.0","event_id":"sha256:a646ce392176477bef8b6a704133b0bded590dd9a69c7929fcffaa4f3a8d0711"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KPSUWKPRIT472FD2HPZOIJUJQA/bundle.json","state_url":"https://pith.science/pith/KPSUWKPRIT472FD2HPZOIJUJQA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KPSUWKPRIT472FD2HPZOIJUJQA/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":"2026-08-08T08:54:26Z","links":{"resolver":"https://pith.science/pith/KPSUWKPRIT472FD2HPZOIJUJQA","bundle":"https://pith.science/pith/KPSUWKPRIT472FD2HPZOIJUJQA/bundle.json","state":"https://pith.science/pith/KPSUWKPRIT472FD2HPZOIJUJQA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KPSUWKPRIT472FD2HPZOIJUJQA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KPSUWKPRIT472FD2HPZOIJUJQA","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":"d30d10b728f02345bd2b276d2b19e89ea919d419df38d74a6cc3a4b446445e5b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T10:45:46Z","title_canon_sha256":"66fbafec92d898a874dda4f6a5789ddfdb905e68ee073875b096cc7a31c0f9a3"},"schema_version":"1.0","source":{"id":"2405.16173","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16173","created_at":"2026-07-05T09:49:42Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16173v3","created_at":"2026-07-05T09:49:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16173","created_at":"2026-07-05T09:49:42Z"},{"alias_kind":"pith_short_12","alias_value":"KPSUWKPRIT47","created_at":"2026-07-05T09:49:42Z"},{"alias_kind":"pith_short_16","alias_value":"KPSUWKPRIT472FD2","created_at":"2026-07-05T09:49:42Z"},{"alias_kind":"pith_short_8","alias_value":"KPSUWKPR","created_at":"2026-07-05T09:49:42Z"}],"graph_snapshots":[{"event_id":"sha256:a646ce392176477bef8b6a704133b0bded590dd9a69c7929fcffaa4f3a8d0711","target":"graph","created_at":"2026-07-05T09:49:42Z","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/2405.16173/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models have garnered widespread attention in Reinforcement Learning (RL) for their powerful expressiveness and multimodality. It has been verified that utilizing diffusion policies can significantly improve the performance of RL algorithms in continuous control tasks by overcoming the limitations of unimodal policies, such as Gaussian policies, and providing the agent with enhanced exploration capabilities. However, existing works mainly focus on the application of diffusion policies in offline RL, while their incorporation into online RL is less investigated. The training objective ","authors_text":"Jingya Wang, Jingyi Yu, Kan Ren, Ke Hu, Shutong Ding, Weinan Zhang, Ye Shi, Zhenhao Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T10:45:46Z","title":"Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16173","kind":"arxiv","version":3},"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":"sha256:86d2eb205c54263fe80849d401436613008dcaaeeed2f42e55978811a6488341","target":"record","created_at":"2026-07-05T09:49:42Z","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":"d30d10b728f02345bd2b276d2b19e89ea919d419df38d74a6cc3a4b446445e5b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T10:45:46Z","title_canon_sha256":"66fbafec92d898a874dda4f6a5789ddfdb905e68ee073875b096cc7a31c0f9a3"},"schema_version":"1.0","source":{"id":"2405.16173","kind":"arxiv","version":3}},"canonical_sha256":"53e54b29f144f9fd147a3bf2e4268980070edb3ac08fdd1707af79b6fecf1c06","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53e54b29f144f9fd147a3bf2e4268980070edb3ac08fdd1707af79b6fecf1c06","first_computed_at":"2026-07-05T09:49:42.841696Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:42.841696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cbLX8EESnAJQ/1aMVT2arlZSAVpfzfuHNzVRnU6JJhYbLqC61KF9/rzFiSrL8zEYppIy3A8uLZh3F84FN1zzDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:42.842180Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16173","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86d2eb205c54263fe80849d401436613008dcaaeeed2f42e55978811a6488341","sha256:a646ce392176477bef8b6a704133b0bded590dd9a69c7929fcffaa4f3a8d0711"],"state_sha256":"1f63fe312b8c9dafc4c72cbcf27e5f290640445ee2b891b5135843d523584930"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cu8YZSct63hAeUUaAcMlNHIUEg1nLEgx8BdlK6t4XoftUIdvtBrHwkFeosCcIF6CV/nD2G2xX+dhY7l5RDJYAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:54:26.899220Z","bundle_sha256":"93548eea5851452a4dbd8075b35a2fb8027879688e02c6200b6ae4a052f5ffcd"}}