{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3GUKGHUY7M4XSAPEZDLXNEYS2Z","short_pith_number":"pith:3GUKGHUY","canonical_record":{"source":{"id":"2310.19733","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-30T16:58:30Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"cebe699d40139599740039ed38b10537ebc80322294ea461d0731479c4cae7bf","abstract_canon_sha256":"88871a9600aefaa5c917da71f99313db4b22cb5be930af785a96c260d4512f55"},"schema_version":"1.0"},"canonical_sha256":"d9a8a31e98fb397901e4c8d7769312d65a3e409f056102aa6842bf86e5e8d422","source":{"kind":"arxiv","id":"2310.19733","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19733","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19733v1","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19733","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"pith_short_12","alias_value":"3GUKGHUY7M4X","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"pith_short_16","alias_value":"3GUKGHUY7M4XSAPE","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"pith_short_8","alias_value":"3GUKGHUY","created_at":"2026-07-05T07:06:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3GUKGHUY7M4XSAPEZDLXNEYS2Z","target":"record","payload":{"canonical_record":{"source":{"id":"2310.19733","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-30T16:58:30Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"cebe699d40139599740039ed38b10537ebc80322294ea461d0731479c4cae7bf","abstract_canon_sha256":"88871a9600aefaa5c917da71f99313db4b22cb5be930af785a96c260d4512f55"},"schema_version":"1.0"},"canonical_sha256":"d9a8a31e98fb397901e4c8d7769312d65a3e409f056102aa6842bf86e5e8d422","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:54.417714Z","signature_b64":"Ij2XRgATlBGXKdTw/92oceb6sWzMjHfarJ/KUp5e2pKlE1Q04OJcZJXtv+9QmyjLmrVXCHUaYLGMDjSPSpWkDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9a8a31e98fb397901e4c8d7769312d65a3e409f056102aa6842bf86e5e8d422","last_reissued_at":"2026-07-05T07:06:54.417225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:54.417225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.19733","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":"2026-07-05T07:06:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Er4OvUB3bG/0aFsQtb8pjvCzDeOhzHZGtRSb9I4g2tYm/TLzwy5VhG9vK6XlXHgfZMkFO265T+/hBv5CdYkYCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T10:59:03.571467Z"},"content_sha256":"0de3e4b1d891a7e52b2e7d96d89ab29ef23bb97cb4ba5ba843de93d0416e7be6","schema_version":"1.0","event_id":"sha256:0de3e4b1d891a7e52b2e7d96d89ab29ef23bb97cb4ba5ba843de93d0416e7be6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3GUKGHUY7M4XSAPEZDLXNEYS2Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Differentially Private Reward Estimation with Preference Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Nagarajan Natarajan, Sayak Ray Chowdhury, Xingyu Zhou","submitted_at":"2023-10-30T16:58:30Z","abstract_excerpt":"Learning from preference-based feedback has recently gained considerable traction as a promising approach to align generative models with human interests. Instead of relying on numerical rewards, the generative models are trained using reinforcement learning with human feedback (RLHF). These approaches first solicit feedback from human labelers typically in the form of pairwise comparisons between two possible actions, then estimate a reward model using these comparisons, and finally employ a policy based on the estimated reward model. An adversarial attack in any step of the above pipeline mi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19733","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/2310.19733/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":"2026-07-05T07:06:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jQUX3KHvWN1zafMEhVfjjlH1mOo0i9gpIHfQ+fa3YLLMN6PVNKv+GMROWW6gtNEkSkK451Tv4kQP1zydJkw/Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T10:59:03.572004Z"},"content_sha256":"03674713eb44848b8f5a238da15e90d1582e06ceeaece9016bcad03bb0cdbde2","schema_version":"1.0","event_id":"sha256:03674713eb44848b8f5a238da15e90d1582e06ceeaece9016bcad03bb0cdbde2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3GUKGHUY7M4XSAPEZDLXNEYS2Z/bundle.json","state_url":"https://pith.science/pith/3GUKGHUY7M4XSAPEZDLXNEYS2Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3GUKGHUY7M4XSAPEZDLXNEYS2Z/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":"2026-08-09T10:59:03Z","links":{"resolver":"https://pith.science/pith/3GUKGHUY7M4XSAPEZDLXNEYS2Z","bundle":"https://pith.science/pith/3GUKGHUY7M4XSAPEZDLXNEYS2Z/bundle.json","state":"https://pith.science/pith/3GUKGHUY7M4XSAPEZDLXNEYS2Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3GUKGHUY7M4XSAPEZDLXNEYS2Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3GUKGHUY7M4XSAPEZDLXNEYS2Z","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":"88871a9600aefaa5c917da71f99313db4b22cb5be930af785a96c260d4512f55","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-30T16:58:30Z","title_canon_sha256":"cebe699d40139599740039ed38b10537ebc80322294ea461d0731479c4cae7bf"},"schema_version":"1.0","source":{"id":"2310.19733","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19733","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19733v1","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19733","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"pith_short_12","alias_value":"3GUKGHUY7M4X","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"pith_short_16","alias_value":"3GUKGHUY7M4XSAPE","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"pith_short_8","alias_value":"3GUKGHUY","created_at":"2026-07-05T07:06:54Z"}],"graph_snapshots":[{"event_id":"sha256:03674713eb44848b8f5a238da15e90d1582e06ceeaece9016bcad03bb0cdbde2","target":"graph","created_at":"2026-07-05T07:06:54Z","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/2310.19733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning from preference-based feedback has recently gained considerable traction as a promising approach to align generative models with human interests. Instead of relying on numerical rewards, the generative models are trained using reinforcement learning with human feedback (RLHF). These approaches first solicit feedback from human labelers typically in the form of pairwise comparisons between two possible actions, then estimate a reward model using these comparisons, and finally employ a policy based on the estimated reward model. An adversarial attack in any step of the above pipeline mi","authors_text":"Nagarajan Natarajan, Sayak Ray Chowdhury, Xingyu Zhou","cross_cats":["cs.CR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-30T16:58:30Z","title":"Differentially Private Reward Estimation with Preference Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19733","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":"sha256:0de3e4b1d891a7e52b2e7d96d89ab29ef23bb97cb4ba5ba843de93d0416e7be6","target":"record","created_at":"2026-07-05T07:06:54Z","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":"88871a9600aefaa5c917da71f99313db4b22cb5be930af785a96c260d4512f55","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-30T16:58:30Z","title_canon_sha256":"cebe699d40139599740039ed38b10537ebc80322294ea461d0731479c4cae7bf"},"schema_version":"1.0","source":{"id":"2310.19733","kind":"arxiv","version":1}},"canonical_sha256":"d9a8a31e98fb397901e4c8d7769312d65a3e409f056102aa6842bf86e5e8d422","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9a8a31e98fb397901e4c8d7769312d65a3e409f056102aa6842bf86e5e8d422","first_computed_at":"2026-07-05T07:06:54.417225Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:54.417225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ij2XRgATlBGXKdTw/92oceb6sWzMjHfarJ/KUp5e2pKlE1Q04OJcZJXtv+9QmyjLmrVXCHUaYLGMDjSPSpWkDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:54.417714Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.19733","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0de3e4b1d891a7e52b2e7d96d89ab29ef23bb97cb4ba5ba843de93d0416e7be6","sha256:03674713eb44848b8f5a238da15e90d1582e06ceeaece9016bcad03bb0cdbde2"],"state_sha256":"090d64f9811b13ffe8d7714c50bb3b8c8f811e14ae4d4e8782f9250c77e84702"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EpLHIQiAqToBFBoYrPtn8AgQX7KqvypauJTTzxAivqQSLBo9bXINEH3j7pvyj408/OCRpZ0tcb7sXkut+64IDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T10:59:03.576697Z","bundle_sha256":"9699eda42f166ee291956991e9798c0129790f68a8c7d41ad2c012b46e62d306"}}