{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5CRLE33SN4PZVRIBUOK552MPAV","short_pith_number":"pith:5CRLE33S","canonical_record":{"source":{"id":"2502.17515","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-22T14:57:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"10f1ce58c805e76ba7e0bb79d0518a97b0aee634cab944c21037aaa9079977c5","abstract_canon_sha256":"d7e62449e2ab55615d85c47c7239d2f12c8b66012681a95a1e3bccafa0939a98"},"schema_version":"1.0"},"canonical_sha256":"e8a2b26f726f1f9ac501a395dee98f057239475e4359324bd2bb1ad577413aea","source":{"kind":"arxiv","id":"2502.17515","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17515","created_at":"2026-07-05T10:19:11Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17515v1","created_at":"2026-07-05T10:19:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17515","created_at":"2026-07-05T10:19:11Z"},{"alias_kind":"pith_short_12","alias_value":"5CRLE33SN4PZ","created_at":"2026-07-05T10:19:11Z"},{"alias_kind":"pith_short_16","alias_value":"5CRLE33SN4PZVRIB","created_at":"2026-07-05T10:19:11Z"},{"alias_kind":"pith_short_8","alias_value":"5CRLE33S","created_at":"2026-07-05T10:19:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5CRLE33SN4PZVRIBUOK552MPAV","target":"record","payload":{"canonical_record":{"source":{"id":"2502.17515","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-22T14:57:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"10f1ce58c805e76ba7e0bb79d0518a97b0aee634cab944c21037aaa9079977c5","abstract_canon_sha256":"d7e62449e2ab55615d85c47c7239d2f12c8b66012681a95a1e3bccafa0939a98"},"schema_version":"1.0"},"canonical_sha256":"e8a2b26f726f1f9ac501a395dee98f057239475e4359324bd2bb1ad577413aea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:11.822749Z","signature_b64":"oYtHg1SMS/AkWUfPWXqd6+DLY2kE/KWvQPCq8CBD+/w0+laW7TS0zik8tvkfmjAXBOT0ZTh2a9eY+biAUDZ+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8a2b26f726f1f9ac501a395dee98f057239475e4359324bd2bb1ad577413aea","last_reissued_at":"2026-07-05T10:19:11.822253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:11.822253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.17515","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:19:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Oh9SnomPAbQBSbX7hr5A/pqxz7yoxWNPwZ/qFiQIzqnRq/TV2TRhEQ2YM7si16gq3aootn3+Xf+zBXZ1fJbIAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:47:35.717220Z"},"content_sha256":"e8401bd444a1dffcab2cd5265cfa96f5256b91b94c35ef3ddaa09940067a0ccd","schema_version":"1.0","event_id":"sha256:e8401bd444a1dffcab2cd5265cfa96f5256b91b94c35ef3ddaa09940067a0ccd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5CRLE33SN4PZVRIBUOK552MPAV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards User-level Private Reinforcement Learning with Human Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Difei Xu, Di Wang, Jiaming Zhang, Jinhui Xu, Mengdi Li, Meng Ding, Mingxi Lei, Zihang Xiang","submitted_at":"2025-02-22T14:57:28Z","abstract_excerpt":"Reinforcement Learning with Human Feedback (RLHF) has emerged as an influential technique, enabling the alignment of large language models (LLMs) with human preferences. Despite the promising potential of RLHF, how to protect user preference privacy has become a crucial issue. Most previous work has focused on using differential privacy (DP) to protect the privacy of individual data. However, they have concentrated primarily on item-level privacy protection and have unsatisfactory performance for user-level privacy, which is more common in RLHF. This study proposes a novel framework, AUP-RLHF,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17515","kind":"arxiv","version":1},"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/2502.17515/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":"2026-07-05T10:19:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mF+IYAEyDDzo4ZjjWtfe733ssZc7ScmknhFtIc3gcZLXA2birxIuURfwzi/vmVnpEOTU9b8pk8DVipD4+WWJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:47:35.717713Z"},"content_sha256":"c346d101e0f42c2c0bfecf7ed79a36d46d06bcd4bb72f0534fbae16ef5327793","schema_version":"1.0","event_id":"sha256:c346d101e0f42c2c0bfecf7ed79a36d46d06bcd4bb72f0534fbae16ef5327793"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5CRLE33SN4PZVRIBUOK552MPAV/bundle.json","state_url":"https://pith.science/pith/5CRLE33SN4PZVRIBUOK552MPAV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5CRLE33SN4PZVRIBUOK552MPAV/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":"2026-08-07T23:47:35Z","links":{"resolver":"https://pith.science/pith/5CRLE33SN4PZVRIBUOK552MPAV","bundle":"https://pith.science/pith/5CRLE33SN4PZVRIBUOK552MPAV/bundle.json","state":"https://pith.science/pith/5CRLE33SN4PZVRIBUOK552MPAV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5CRLE33SN4PZVRIBUOK552MPAV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5CRLE33SN4PZVRIBUOK552MPAV","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":"d7e62449e2ab55615d85c47c7239d2f12c8b66012681a95a1e3bccafa0939a98","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-22T14:57:28Z","title_canon_sha256":"10f1ce58c805e76ba7e0bb79d0518a97b0aee634cab944c21037aaa9079977c5"},"schema_version":"1.0","source":{"id":"2502.17515","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17515","created_at":"2026-07-05T10:19:11Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17515v1","created_at":"2026-07-05T10:19:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17515","created_at":"2026-07-05T10:19:11Z"},{"alias_kind":"pith_short_12","alias_value":"5CRLE33SN4PZ","created_at":"2026-07-05T10:19:11Z"},{"alias_kind":"pith_short_16","alias_value":"5CRLE33SN4PZVRIB","created_at":"2026-07-05T10:19:11Z"},{"alias_kind":"pith_short_8","alias_value":"5CRLE33S","created_at":"2026-07-05T10:19:11Z"}],"graph_snapshots":[{"event_id":"sha256:c346d101e0f42c2c0bfecf7ed79a36d46d06bcd4bb72f0534fbae16ef5327793","target":"graph","created_at":"2026-07-05T10:19:11Z","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/2502.17515/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning with Human Feedback (RLHF) has emerged as an influential technique, enabling the alignment of large language models (LLMs) with human preferences. Despite the promising potential of RLHF, how to protect user preference privacy has become a crucial issue. Most previous work has focused on using differential privacy (DP) to protect the privacy of individual data. However, they have concentrated primarily on item-level privacy protection and have unsatisfactory performance for user-level privacy, which is more common in RLHF. This study proposes a novel framework, AUP-RLHF,","authors_text":"Difei Xu, Di Wang, Jiaming Zhang, Jinhui Xu, Mengdi Li, Meng Ding, Mingxi Lei, Zihang Xiang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-22T14:57:28Z","title":"Towards User-level Private Reinforcement Learning with Human Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17515","kind":"arxiv","version":1},"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:e8401bd444a1dffcab2cd5265cfa96f5256b91b94c35ef3ddaa09940067a0ccd","target":"record","created_at":"2026-07-05T10:19:11Z","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":"d7e62449e2ab55615d85c47c7239d2f12c8b66012681a95a1e3bccafa0939a98","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-22T14:57:28Z","title_canon_sha256":"10f1ce58c805e76ba7e0bb79d0518a97b0aee634cab944c21037aaa9079977c5"},"schema_version":"1.0","source":{"id":"2502.17515","kind":"arxiv","version":1}},"canonical_sha256":"e8a2b26f726f1f9ac501a395dee98f057239475e4359324bd2bb1ad577413aea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8a2b26f726f1f9ac501a395dee98f057239475e4359324bd2bb1ad577413aea","first_computed_at":"2026-07-05T10:19:11.822253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:11.822253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oYtHg1SMS/AkWUfPWXqd6+DLY2kE/KWvQPCq8CBD+/w0+laW7TS0zik8tvkfmjAXBOT0ZTh2a9eY+biAUDZ+Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:11.822749Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.17515","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8401bd444a1dffcab2cd5265cfa96f5256b91b94c35ef3ddaa09940067a0ccd","sha256:c346d101e0f42c2c0bfecf7ed79a36d46d06bcd4bb72f0534fbae16ef5327793"],"state_sha256":"58677c33e82e7c6099786604d1e73ccff9e6738e6837d8ecbac397ccad72573d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"86nwujUSNR5pWY3VKCDrJAviVFE3NsZk37i6UZDwQwSHhzbjeFi5esBoU0NGnWEP1VmeHNFwwUzmJNPPdbd7Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:47:35.721777Z","bundle_sha256":"c62a1ed5cacf17c85d73e0fad6c9ea98f9b162427b798026057e20ddbf6503a8"}}