{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LUJ2KHPMS3GAFJNNK3BG5IBXX6","short_pith_number":"pith:LUJ2KHPM","canonical_record":{"source":{"id":"2510.21060","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-24T00:21:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"35c2cc68e8a0904a0cd9fc4a3d454ea879bd4f23cf3e0077591495ae6ff678d1","abstract_canon_sha256":"b18d27abeb14c1c91c74dfabecd269d1543e85a0c5fecb5fbc7caea264990101"},"schema_version":"1.0"},"canonical_sha256":"5d13a51dec96cc02a5ad56c26ea037bf9eaed7ad5db4b0603598335fac2ce6f3","source":{"kind":"arxiv","id":"2510.21060","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.21060","created_at":"2026-05-18T03:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"2510.21060v3","created_at":"2026-05-18T03:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.21060","created_at":"2026-05-18T03:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"LUJ2KHPMS3GA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"LUJ2KHPMS3GAFJNN","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"LUJ2KHPM","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LUJ2KHPMS3GAFJNNK3BG5IBXX6","target":"record","payload":{"canonical_record":{"source":{"id":"2510.21060","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-24T00:21:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"35c2cc68e8a0904a0cd9fc4a3d454ea879bd4f23cf3e0077591495ae6ff678d1","abstract_canon_sha256":"b18d27abeb14c1c91c74dfabecd269d1543e85a0c5fecb5fbc7caea264990101"},"schema_version":"1.0"},"canonical_sha256":"5d13a51dec96cc02a5ad56c26ea037bf9eaed7ad5db4b0603598335fac2ce6f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:33.717786Z","signature_b64":"xKb7m4WqPJra+8N3w9aMhIgw3ihmv2L5cJYfXiZTDzi8K1eIraDrhBeoV9fMsegjvG68LkB620LIpMvpSSQhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d13a51dec96cc02a5ad56c26ea037bf9eaed7ad5db4b0603598335fac2ce6f3","last_reissued_at":"2026-05-18T03:09:33.717329Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:33.717329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.21060","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":"2026-05-18T03:09:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ucOAzz2NlkVLl5uHTbPExLe3Ki/FCBdtYLZ1xQmSrcB+9d7j/hlrcDkoJ8QIm3Xn+cEA5f6MQeSl30bqMIkVDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T13:01:18.292863Z"},"content_sha256":"537e95ccd8fabed5207d0c745bd44c2bec04369fbbc0bd39741d8eb8c6b64d8e","schema_version":"1.0","event_id":"sha256:537e95ccd8fabed5207d0c745bd44c2bec04369fbbc0bd39741d8eb8c6b64d8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LUJ2KHPMS3GAFJNNK3BG5IBXX6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Sample Complexity of Differentially Private Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Xingyu Zhou, Yi He","submitted_at":"2025-10-24T00:21:38Z","abstract_excerpt":"Policy optimization (PO) is a cornerstone of modern reinforcement learning (RL), with diverse applications spanning robotics, healthcare, and large language model training. The increasing deployment of PO in sensitive domains, however, raises significant privacy concerns. In this paper, we initiate a theoretical study of differentially private policy optimization, focusing explicitly on its sample complexity. We first formalize an appropriate definition of differential privacy (DP) tailored to PO, addressing the inherent challenges arising from on-policy learning dynamics and the subtlety invo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.21060","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":""},"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":"2026-05-18T03:09:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i/9Z93gV7Wdonv5oKo9qAIZTwIXywHoTRhqdDF2m76i52LgqJJEh+SzVKxYe/DfV+okP3z3yN+HldvAccsMLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T13:01:18.293516Z"},"content_sha256":"d85dcdd8bbfc2f134691b629ebb8f8e021c7c1215f584f7d8454bb5e4a7c3fb4","schema_version":"1.0","event_id":"sha256:d85dcdd8bbfc2f134691b629ebb8f8e021c7c1215f584f7d8454bb5e4a7c3fb4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LUJ2KHPMS3GAFJNNK3BG5IBXX6/bundle.json","state_url":"https://pith.science/pith/LUJ2KHPMS3GAFJNNK3BG5IBXX6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LUJ2KHPMS3GAFJNNK3BG5IBXX6/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":"2026-05-21T13:01:18Z","links":{"resolver":"https://pith.science/pith/LUJ2KHPMS3GAFJNNK3BG5IBXX6","bundle":"https://pith.science/pith/LUJ2KHPMS3GAFJNNK3BG5IBXX6/bundle.json","state":"https://pith.science/pith/LUJ2KHPMS3GAFJNNK3BG5IBXX6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LUJ2KHPMS3GAFJNNK3BG5IBXX6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LUJ2KHPMS3GAFJNNK3BG5IBXX6","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":"b18d27abeb14c1c91c74dfabecd269d1543e85a0c5fecb5fbc7caea264990101","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-24T00:21:38Z","title_canon_sha256":"35c2cc68e8a0904a0cd9fc4a3d454ea879bd4f23cf3e0077591495ae6ff678d1"},"schema_version":"1.0","source":{"id":"2510.21060","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.21060","created_at":"2026-05-18T03:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"2510.21060v3","created_at":"2026-05-18T03:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.21060","created_at":"2026-05-18T03:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"LUJ2KHPMS3GA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"LUJ2KHPMS3GAFJNN","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"LUJ2KHPM","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:d85dcdd8bbfc2f134691b629ebb8f8e021c7c1215f584f7d8454bb5e4a7c3fb4","target":"graph","created_at":"2026-05-18T03:09:33Z","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"},"paper":{"abstract_excerpt":"Policy optimization (PO) is a cornerstone of modern reinforcement learning (RL), with diverse applications spanning robotics, healthcare, and large language model training. The increasing deployment of PO in sensitive domains, however, raises significant privacy concerns. In this paper, we initiate a theoretical study of differentially private policy optimization, focusing explicitly on its sample complexity. We first formalize an appropriate definition of differential privacy (DP) tailored to PO, addressing the inherent challenges arising from on-policy learning dynamics and the subtlety invo","authors_text":"Xingyu Zhou, Yi He","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-24T00:21:38Z","title":"On the Sample Complexity of Differentially Private Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.21060","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":"sha256:537e95ccd8fabed5207d0c745bd44c2bec04369fbbc0bd39741d8eb8c6b64d8e","target":"record","created_at":"2026-05-18T03:09:33Z","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":"b18d27abeb14c1c91c74dfabecd269d1543e85a0c5fecb5fbc7caea264990101","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-24T00:21:38Z","title_canon_sha256":"35c2cc68e8a0904a0cd9fc4a3d454ea879bd4f23cf3e0077591495ae6ff678d1"},"schema_version":"1.0","source":{"id":"2510.21060","kind":"arxiv","version":3}},"canonical_sha256":"5d13a51dec96cc02a5ad56c26ea037bf9eaed7ad5db4b0603598335fac2ce6f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d13a51dec96cc02a5ad56c26ea037bf9eaed7ad5db4b0603598335fac2ce6f3","first_computed_at":"2026-05-18T03:09:33.717329Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:33.717329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xKb7m4WqPJra+8N3w9aMhIgw3ihmv2L5cJYfXiZTDzi8K1eIraDrhBeoV9fMsegjvG68LkB620LIpMvpSSQhCw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:33.717786Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.21060","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:537e95ccd8fabed5207d0c745bd44c2bec04369fbbc0bd39741d8eb8c6b64d8e","sha256:d85dcdd8bbfc2f134691b629ebb8f8e021c7c1215f584f7d8454bb5e4a7c3fb4"],"state_sha256":"67ea5afe9263ba532edc4fc6e2439f3d5e9ea70e81511d7140c4700e95064071"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XK76UKExVCKXIL7WcAxVR1ws2il3P38IwGsU6ODd5gZfPooicPlh7Ds3IAtBDviKeajBwPYySWkf7ybN0j0lBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T13:01:18.296837Z","bundle_sha256":"c679372409f16e7187a89b6b3515adefadd717768856711a125cf020131e355f"}}