{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NW6OMQRBQ6KQWL7ZNLTZAKBSPF","short_pith_number":"pith:NW6OMQRB","canonical_record":{"source":{"id":"2310.07297","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T08:31:26Z","cross_cats_sorted":[],"title_canon_sha256":"04b07219c12228259ce30d056951688d08fea9676abfa959211e55d25d89e4c4","abstract_canon_sha256":"e0f96e5a4b582ae4632ece97c67c07713f61e79d687617c559f876817ba1d930"},"schema_version":"1.0"},"canonical_sha256":"6dbce6422187950b2ff96ae7902832794bf692a8d4d8c17bdaeb4803c57db44d","source":{"kind":"arxiv","id":"2310.07297","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07297","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07297v3","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07297","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"pith_short_12","alias_value":"NW6OMQRBQ6KQ","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"pith_short_16","alias_value":"NW6OMQRBQ6KQWL7Z","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"pith_short_8","alias_value":"NW6OMQRB","created_at":"2026-07-05T07:56:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NW6OMQRBQ6KQWL7ZNLTZAKBSPF","target":"record","payload":{"canonical_record":{"source":{"id":"2310.07297","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T08:31:26Z","cross_cats_sorted":[],"title_canon_sha256":"04b07219c12228259ce30d056951688d08fea9676abfa959211e55d25d89e4c4","abstract_canon_sha256":"e0f96e5a4b582ae4632ece97c67c07713f61e79d687617c559f876817ba1d930"},"schema_version":"1.0"},"canonical_sha256":"6dbce6422187950b2ff96ae7902832794bf692a8d4d8c17bdaeb4803c57db44d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:17.552270Z","signature_b64":"ADyJpr5U4IKGebScjLEIHamrSp7mg8ZQTmAGSj/1E/MphoHH1CHOI02N5WiNHIQd1ltiHhXiBFLW5k8/N3gfAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dbce6422187950b2ff96ae7902832794bf692a8d4d8c17bdaeb4803c57db44d","last_reissued_at":"2026-07-05T07:56:17.551819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:17.551819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.07297","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":"2026-07-05T07:56:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UfK0q1RO1ovd35oAX55O3rYwuJoytiLvvM3MPOIl3UC9Gqi/cMF4cOqn1mkAfZ4Vmeuo+4Y3Rmq9b64lNpbkDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T04:04:04.213465Z"},"content_sha256":"f56485cfd3b0a06ec2ab310f5e6a55cf46eed7ee3e20dbd0fa816a2bbdfbc3e0","schema_version":"1.0","event_id":"sha256:f56485cfd3b0a06ec2ab310f5e6a55cf46eed7ee3e20dbd0fa816a2bbdfbc3e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NW6OMQRBQ6KQWL7ZNLTZAKBSPF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Score Regularized Policy Optimization through Diffusion Behavior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cheng Lu, Hang Su, Huayu Chen, Jun Zhu, Zhengyi Wang","submitted_at":"2023-10-11T08:31:26Z","abstract_excerpt":"Recent developments in offline reinforcement learning have uncovered the immense potential of diffusion modeling, which excels at representing heterogeneous behavior policies. However, sampling from diffusion policies is considerably slow because it necessitates tens to hundreds of iterative inference steps for one action. To address this issue, we propose to extract an efficient deterministic inference policy from critic models and pretrained diffusion behavior models, leveraging the latter to directly regularize the policy gradient with the behavior distribution's score function during optim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07297","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/2310.07297/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":"xm0jIfx9JgM6/V8Ae96Uber1J+RC8t3m+Efh+Txqa/wzfi4QC8yDbztO0Z8VBg9fMD3fWrSfrEW/u9hmJJVWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T04:04:04.213854Z"},"content_sha256":"1e65d29c1848156959aed3d234e95cb4d1a3f702ab71b4814672df34c83b2f18","schema_version":"1.0","event_id":"sha256:1e65d29c1848156959aed3d234e95cb4d1a3f702ab71b4814672df34c83b2f18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NW6OMQRBQ6KQWL7ZNLTZAKBSPF/bundle.json","state_url":"https://pith.science/pith/NW6OMQRBQ6KQWL7ZNLTZAKBSPF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NW6OMQRBQ6KQWL7ZNLTZAKBSPF/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":"2026-08-12T04:04:04Z","links":{"resolver":"https://pith.science/pith/NW6OMQRBQ6KQWL7ZNLTZAKBSPF","bundle":"https://pith.science/pith/NW6OMQRBQ6KQWL7ZNLTZAKBSPF/bundle.json","state":"https://pith.science/pith/NW6OMQRBQ6KQWL7ZNLTZAKBSPF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NW6OMQRBQ6KQWL7ZNLTZAKBSPF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NW6OMQRBQ6KQWL7ZNLTZAKBSPF","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":"e0f96e5a4b582ae4632ece97c67c07713f61e79d687617c559f876817ba1d930","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T08:31:26Z","title_canon_sha256":"04b07219c12228259ce30d056951688d08fea9676abfa959211e55d25d89e4c4"},"schema_version":"1.0","source":{"id":"2310.07297","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07297","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07297v3","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07297","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"pith_short_12","alias_value":"NW6OMQRBQ6KQ","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"pith_short_16","alias_value":"NW6OMQRBQ6KQWL7Z","created_at":"2026-07-05T07:56:17Z"},{"alias_kind":"pith_short_8","alias_value":"NW6OMQRB","created_at":"2026-07-05T07:56:17Z"}],"graph_snapshots":[{"event_id":"sha256:1e65d29c1848156959aed3d234e95cb4d1a3f702ab71b4814672df34c83b2f18","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/2310.07297/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent developments in offline reinforcement learning have uncovered the immense potential of diffusion modeling, which excels at representing heterogeneous behavior policies. However, sampling from diffusion policies is considerably slow because it necessitates tens to hundreds of iterative inference steps for one action. To address this issue, we propose to extract an efficient deterministic inference policy from critic models and pretrained diffusion behavior models, leveraging the latter to directly regularize the policy gradient with the behavior distribution's score function during optim","authors_text":"Cheng Lu, Hang Su, Huayu Chen, Jun Zhu, Zhengyi Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T08:31:26Z","title":"Score Regularized Policy Optimization through Diffusion Behavior"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07297","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:f56485cfd3b0a06ec2ab310f5e6a55cf46eed7ee3e20dbd0fa816a2bbdfbc3e0","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":"e0f96e5a4b582ae4632ece97c67c07713f61e79d687617c559f876817ba1d930","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T08:31:26Z","title_canon_sha256":"04b07219c12228259ce30d056951688d08fea9676abfa959211e55d25d89e4c4"},"schema_version":"1.0","source":{"id":"2310.07297","kind":"arxiv","version":3}},"canonical_sha256":"6dbce6422187950b2ff96ae7902832794bf692a8d4d8c17bdaeb4803c57db44d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6dbce6422187950b2ff96ae7902832794bf692a8d4d8c17bdaeb4803c57db44d","first_computed_at":"2026-07-05T07:56:17.551819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:17.551819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ADyJpr5U4IKGebScjLEIHamrSp7mg8ZQTmAGSj/1E/MphoHH1CHOI02N5WiNHIQd1ltiHhXiBFLW5k8/N3gfAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:17.552270Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.07297","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f56485cfd3b0a06ec2ab310f5e6a55cf46eed7ee3e20dbd0fa816a2bbdfbc3e0","sha256:1e65d29c1848156959aed3d234e95cb4d1a3f702ab71b4814672df34c83b2f18"],"state_sha256":"fb13778ce19ccda1b0369bd7b8b99093cd42b9ae814bad5f65977949030bd3b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ghw6iGPUGQYGCd4p00PTsZLICybk940zqFAji2xcs5C3QfE5AIfy3VJtq8JUu/g6ZbMBl4c5pB3dYMaonZDmBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T04:04:04.217354Z","bundle_sha256":"db27bb70a9bd2d996216ea45d4770c70c770d476c9095120c9a2ca993a03c93b"}}