{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HXMXM3GMM5OTKVQWOQNV7GBKPU","short_pith_number":"pith:HXMXM3GM","canonical_record":{"source":{"id":"2502.04778","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-07T09:30:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"736dbad9c6339fe71aa666e2c8ccd2f6efd15a000422631c44d67d4fa3dd08e0","abstract_canon_sha256":"4b173df43185d094080020cb3b964e39b113a06a98ea24e4a4113533f18d9a33"},"schema_version":"1.0"},"canonical_sha256":"3dd9766ccc675d355616741b5f982a7d0d68b2b80410e3cd3297dcdf53a0817e","source":{"kind":"arxiv","id":"2502.04778","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04778","created_at":"2026-07-05T11:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04778v2","created_at":"2026-07-05T11:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04778","created_at":"2026-07-05T11:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"HXMXM3GMM5OT","created_at":"2026-07-05T11:11:40Z"},{"alias_kind":"pith_short_16","alias_value":"HXMXM3GMM5OTKVQW","created_at":"2026-07-05T11:11:40Z"},{"alias_kind":"pith_short_8","alias_value":"HXMXM3GM","created_at":"2026-07-05T11:11:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HXMXM3GMM5OTKVQWOQNV7GBKPU","target":"record","payload":{"canonical_record":{"source":{"id":"2502.04778","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-07T09:30:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"736dbad9c6339fe71aa666e2c8ccd2f6efd15a000422631c44d67d4fa3dd08e0","abstract_canon_sha256":"4b173df43185d094080020cb3b964e39b113a06a98ea24e4a4113533f18d9a33"},"schema_version":"1.0"},"canonical_sha256":"3dd9766ccc675d355616741b5f982a7d0d68b2b80410e3cd3297dcdf53a0817e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:40.926735Z","signature_b64":"G9k3QxnqAvApenj2WOC45Fq0iHlcgQHGvTjB1WFfZYlBqRASbeHhiLu+71Kl5xDaDeZyWuQUWCAsASvWKI3uAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dd9766ccc675d355616741b5f982a7d0d68b2b80410e3cd3297dcdf53a0817e","last_reissued_at":"2026-07-05T11:11:40.926224Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:40.926224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.04778","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":"2026-07-05T11:11:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4NmOkth/+YCRAaTS6MGAbxF/vsVwzoEa5Z3GK+0cJ0BuYE203rKLNnYahfkPVFjXzqAOdCrsU6QRWUbO4uqeBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T03:27:07.098971Z"},"content_sha256":"9ccd96ec6e7eab65b07356f7d7d1a8b4f6a22fc2565459b0bb8181641ae32d0d","schema_version":"1.0","event_id":"sha256:9ccd96ec6e7eab65b07356f7d7d1a8b4f6a22fc2565459b0bb8181641ae32d0d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HXMXM3GMM5OTKVQWOQNV7GBKPU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenjun Xiao, Chen-Xiao Gao, Chenyang Wu, Mingjun Cao, Yang Yu, Zongzhang Zhang","submitted_at":"2025-02-07T09:30:35Z","abstract_excerpt":"Behavior regularization, which constrains the policy to stay close to some behavior policy, is widely used in offline reinforcement learning (RL) to manage the risk of hazardous exploitation of unseen actions. Nevertheless, existing literature on behavior-regularized RL primarily focuses on explicit policy parameterizations, such as Gaussian policies. Consequently, it remains unclear how to extend this framework to more advanced policy parameterizations, such as diffusion models. In this paper, we introduce BDPO, a principled behavior-regularized RL framework tailored for diffusion-based polic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04778","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/2502.04778/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":"2026-07-05T11:11:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UQkQi137f28mQCMsS+co4eIwZUfCY1Zd0Xuuf1XY343Z4JKwU9SzwBANciwCkctYdhgVnsUY5qAr9Wz4J4ORBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T03:27:07.099471Z"},"content_sha256":"7b6dadc5fa10f0719c34b325f5576b168b1cfdbdaa54ef70411c4fa10dce9229","schema_version":"1.0","event_id":"sha256:7b6dadc5fa10f0719c34b325f5576b168b1cfdbdaa54ef70411c4fa10dce9229"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HXMXM3GMM5OTKVQWOQNV7GBKPU/bundle.json","state_url":"https://pith.science/pith/HXMXM3GMM5OTKVQWOQNV7GBKPU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HXMXM3GMM5OTKVQWOQNV7GBKPU/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":"2026-08-13T03:27:07Z","links":{"resolver":"https://pith.science/pith/HXMXM3GMM5OTKVQWOQNV7GBKPU","bundle":"https://pith.science/pith/HXMXM3GMM5OTKVQWOQNV7GBKPU/bundle.json","state":"https://pith.science/pith/HXMXM3GMM5OTKVQWOQNV7GBKPU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HXMXM3GMM5OTKVQWOQNV7GBKPU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HXMXM3GMM5OTKVQWOQNV7GBKPU","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":"4b173df43185d094080020cb3b964e39b113a06a98ea24e4a4113533f18d9a33","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-07T09:30:35Z","title_canon_sha256":"736dbad9c6339fe71aa666e2c8ccd2f6efd15a000422631c44d67d4fa3dd08e0"},"schema_version":"1.0","source":{"id":"2502.04778","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04778","created_at":"2026-07-05T11:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04778v2","created_at":"2026-07-05T11:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04778","created_at":"2026-07-05T11:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"HXMXM3GMM5OT","created_at":"2026-07-05T11:11:40Z"},{"alias_kind":"pith_short_16","alias_value":"HXMXM3GMM5OTKVQW","created_at":"2026-07-05T11:11:40Z"},{"alias_kind":"pith_short_8","alias_value":"HXMXM3GM","created_at":"2026-07-05T11:11:40Z"}],"graph_snapshots":[{"event_id":"sha256:7b6dadc5fa10f0719c34b325f5576b168b1cfdbdaa54ef70411c4fa10dce9229","target":"graph","created_at":"2026-07-05T11:11:40Z","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/2502.04778/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Behavior regularization, which constrains the policy to stay close to some behavior policy, is widely used in offline reinforcement learning (RL) to manage the risk of hazardous exploitation of unseen actions. Nevertheless, existing literature on behavior-regularized RL primarily focuses on explicit policy parameterizations, such as Gaussian policies. Consequently, it remains unclear how to extend this framework to more advanced policy parameterizations, such as diffusion models. In this paper, we introduce BDPO, a principled behavior-regularized RL framework tailored for diffusion-based polic","authors_text":"Chenjun Xiao, Chen-Xiao Gao, Chenyang Wu, Mingjun Cao, Yang Yu, Zongzhang Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-07T09:30:35Z","title":"Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04778","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":"sha256:9ccd96ec6e7eab65b07356f7d7d1a8b4f6a22fc2565459b0bb8181641ae32d0d","target":"record","created_at":"2026-07-05T11:11:40Z","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":"4b173df43185d094080020cb3b964e39b113a06a98ea24e4a4113533f18d9a33","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-07T09:30:35Z","title_canon_sha256":"736dbad9c6339fe71aa666e2c8ccd2f6efd15a000422631c44d67d4fa3dd08e0"},"schema_version":"1.0","source":{"id":"2502.04778","kind":"arxiv","version":2}},"canonical_sha256":"3dd9766ccc675d355616741b5f982a7d0d68b2b80410e3cd3297dcdf53a0817e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3dd9766ccc675d355616741b5f982a7d0d68b2b80410e3cd3297dcdf53a0817e","first_computed_at":"2026-07-05T11:11:40.926224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:40.926224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G9k3QxnqAvApenj2WOC45Fq0iHlcgQHGvTjB1WFfZYlBqRASbeHhiLu+71Kl5xDaDeZyWuQUWCAsASvWKI3uAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:40.926735Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04778","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ccd96ec6e7eab65b07356f7d7d1a8b4f6a22fc2565459b0bb8181641ae32d0d","sha256:7b6dadc5fa10f0719c34b325f5576b168b1cfdbdaa54ef70411c4fa10dce9229"],"state_sha256":"5efb9dd2517988e6c10658208bd4cd6f62d2088c929d6fbf5fe6924a5fc6fb7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lJ6LFxxvdvB/4r0b0L40tkwiSXWZa6UJiLvMq6a/9YeWaiNpGr//b82+oCG5FqQimYm+SR9+fW6HsRBWkGYBBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T03:27:07.104536Z","bundle_sha256":"2b7ef95afe0eed6319434e85ba59d7ce692460462871a7db204631a0dcb049c6"}}