{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:HHNR2WVKBTWUS64LMWY7T2P2ED","short_pith_number":"pith:HHNR2WVK","canonical_record":{"source":{"id":"2309.16984","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-29T05:05:54Z","cross_cats_sorted":[],"title_canon_sha256":"4b0efd49ad135ef085793a339d4f12c2f14c98931a1c4c71172cccdf47c457c5","abstract_canon_sha256":"67195acdb9c4d460dce5c7845bd73f6f7c8b225118231675126631631ca62919"},"schema_version":"1.0"},"canonical_sha256":"39db1d5aaa0ced497b8b65b1f9e9fa20c8a9410f7f99aea59192a6622e113839","source":{"kind":"arxiv","id":"2309.16984","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.16984","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"arxiv_version","alias_value":"2309.16984v2","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16984","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"pith_short_12","alias_value":"HHNR2WVKBTWU","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"pith_short_16","alias_value":"HHNR2WVKBTWUS64L","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"pith_short_8","alias_value":"HHNR2WVK","created_at":"2026-07-05T07:56:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:HHNR2WVKBTWUS64LMWY7T2P2ED","target":"record","payload":{"canonical_record":{"source":{"id":"2309.16984","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-29T05:05:54Z","cross_cats_sorted":[],"title_canon_sha256":"4b0efd49ad135ef085793a339d4f12c2f14c98931a1c4c71172cccdf47c457c5","abstract_canon_sha256":"67195acdb9c4d460dce5c7845bd73f6f7c8b225118231675126631631ca62919"},"schema_version":"1.0"},"canonical_sha256":"39db1d5aaa0ced497b8b65b1f9e9fa20c8a9410f7f99aea59192a6622e113839","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:17.217042Z","signature_b64":"9OKpPeslSpU1dt85uDfTudPR7kzkM1jLYevLLZzJL2kgdEOkhf7LKBeqo/Z/brX2WjX0n+8VxWZNYByHZzTBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39db1d5aaa0ced497b8b65b1f9e9fa20c8a9410f7f99aea59192a6622e113839","last_reissued_at":"2026-07-05T07:56:17.216601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:17.216601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.16984","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:56:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8LmM+Z5LCK95XPSjVQSnIs+RoLMMhgkifmqJHPUfSvgI4Nq8ZlVRy+hRmUZK/Ps+En89FnDVNHTf7FA6jhazCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:51:24.483938Z"},"content_sha256":"70c647668547ebf02a48e7232dd66587a149ed01260364882612a3e1ddfa19d4","schema_version":"1.0","event_id":"sha256:70c647668547ebf02a48e7232dd66587a149ed01260364882612a3e1ddfa19d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:HHNR2WVKBTWUS64LMWY7T2P2ED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chi Jin, Zihan Ding","submitted_at":"2023-09-29T05:05:54Z","abstract_excerpt":"Score-based generative models like the diffusion model have been testified to be effective in modeling multi-modal data from image generation to reinforcement learning (RL). However, the inference process of diffusion model can be slow, which hinders its usage in RL with iterative sampling. We propose to apply the consistency model as an efficient yet expressive policy representation, namely consistency policy, with an actor-critic style algorithm for three typical RL settings: offline, offline-to-online and online. For offline RL, we demonstrate the expressiveness of generative models as poli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16984","kind":"arxiv","version":2},"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/2309.16984/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":"2026-07-05T07:56:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w6QdoKXoKTR+/pBkBSByTLS7nxqPq2pWHJWwmHCwXgAwaFDAJJcD+3fhl0LJUXOxg3oXEh5IAh8Uau6i4mS/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:51:24.484435Z"},"content_sha256":"36ea488f5a69c67635f27bb1993de6dc1af81332f87849ee0264aa480bc9c351","schema_version":"1.0","event_id":"sha256:36ea488f5a69c67635f27bb1993de6dc1af81332f87849ee0264aa480bc9c351"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HHNR2WVKBTWUS64LMWY7T2P2ED/bundle.json","state_url":"https://pith.science/pith/HHNR2WVKBTWUS64LMWY7T2P2ED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HHNR2WVKBTWUS64LMWY7T2P2ED/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":"2026-08-04T14:51:24Z","links":{"resolver":"https://pith.science/pith/HHNR2WVKBTWUS64LMWY7T2P2ED","bundle":"https://pith.science/pith/HHNR2WVKBTWUS64LMWY7T2P2ED/bundle.json","state":"https://pith.science/pith/HHNR2WVKBTWUS64LMWY7T2P2ED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HHNR2WVKBTWUS64LMWY7T2P2ED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HHNR2WVKBTWUS64LMWY7T2P2ED","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":"67195acdb9c4d460dce5c7845bd73f6f7c8b225118231675126631631ca62919","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-29T05:05:54Z","title_canon_sha256":"4b0efd49ad135ef085793a339d4f12c2f14c98931a1c4c71172cccdf47c457c5"},"schema_version":"1.0","source":{"id":"2309.16984","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.16984","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"arxiv_version","alias_value":"2309.16984v2","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16984","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"pith_short_12","alias_value":"HHNR2WVKBTWU","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"pith_short_16","alias_value":"HHNR2WVKBTWUS64L","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"pith_short_8","alias_value":"HHNR2WVK","created_at":"2026-07-05T07:56:17Z"}],"graph_snapshots":[{"event_id":"sha256:36ea488f5a69c67635f27bb1993de6dc1af81332f87849ee0264aa480bc9c351","target":"graph","created_at":"2026-07-05T07:56:17Z","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/2309.16984/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Score-based generative models like the diffusion model have been testified to be effective in modeling multi-modal data from image generation to reinforcement learning (RL). However, the inference process of diffusion model can be slow, which hinders its usage in RL with iterative sampling. We propose to apply the consistency model as an efficient yet expressive policy representation, namely consistency policy, with an actor-critic style algorithm for three typical RL settings: offline, offline-to-online and online. For offline RL, we demonstrate the expressiveness of generative models as poli","authors_text":"Chi Jin, Zihan Ding","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-29T05:05:54Z","title":"Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16984","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":"sha256:70c647668547ebf02a48e7232dd66587a149ed01260364882612a3e1ddfa19d4","target":"record","created_at":"2026-07-05T07:56:17Z","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":"67195acdb9c4d460dce5c7845bd73f6f7c8b225118231675126631631ca62919","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-29T05:05:54Z","title_canon_sha256":"4b0efd49ad135ef085793a339d4f12c2f14c98931a1c4c71172cccdf47c457c5"},"schema_version":"1.0","source":{"id":"2309.16984","kind":"arxiv","version":2}},"canonical_sha256":"39db1d5aaa0ced497b8b65b1f9e9fa20c8a9410f7f99aea59192a6622e113839","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39db1d5aaa0ced497b8b65b1f9e9fa20c8a9410f7f99aea59192a6622e113839","first_computed_at":"2026-07-05T07:56:17.216601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:17.216601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9OKpPeslSpU1dt85uDfTudPR7kzkM1jLYevLLZzJL2kgdEOkhf7LKBeqo/Z/brX2WjX0n+8VxWZNYByHZzTBAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:17.217042Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.16984","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70c647668547ebf02a48e7232dd66587a149ed01260364882612a3e1ddfa19d4","sha256:36ea488f5a69c67635f27bb1993de6dc1af81332f87849ee0264aa480bc9c351"],"state_sha256":"6322e5c2d4fb4eb6e284114feb496b4c9577e885efcb5bb787dbbddad92d0de4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fJksqpsL6OrnmT91k81eVF8MjY34RSyPkldWC6F1BhZMuXjbt18XyE0V7QMKpecsHfEnyHnCB4XQNDldUcNVDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T14:51:24.488132Z","bundle_sha256":"83340058be15bbbb91bae6deebcd08e9bac0987989e38ab5af1fe02d6e00e811"}}