{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OWFH7LSGLZW5CK2DA2K5AR4V52","short_pith_number":"pith:OWFH7LSG","canonical_record":{"source":{"id":"2505.24603","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T13:52:48Z","cross_cats_sorted":[],"title_canon_sha256":"88bf34186061318d89dbc2bb06c5d4c0fb323e0518bf702238b7bacb135cfd09","abstract_canon_sha256":"29b39d7e2151625261bc224be22ccade109402fb6710974531438525cbeaf503"},"schema_version":"1.0"},"canonical_sha256":"758a7fae465e6dd12b430695d04795eea8a7a4b2eb3be5aa400aabc662d22e08","source":{"kind":"arxiv","id":"2505.24603","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24603","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24603v2","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24603","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_12","alias_value":"OWFH7LSGLZW5","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_16","alias_value":"OWFH7LSGLZW5CK2D","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_8","alias_value":"OWFH7LSG","created_at":"2026-07-05T11:15:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OWFH7LSGLZW5CK2DA2K5AR4V52","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24603","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T13:52:48Z","cross_cats_sorted":[],"title_canon_sha256":"88bf34186061318d89dbc2bb06c5d4c0fb323e0518bf702238b7bacb135cfd09","abstract_canon_sha256":"29b39d7e2151625261bc224be22ccade109402fb6710974531438525cbeaf503"},"schema_version":"1.0"},"canonical_sha256":"758a7fae465e6dd12b430695d04795eea8a7a4b2eb3be5aa400aabc662d22e08","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:47.362063Z","signature_b64":"b29M3g1jFF124dfWvGqai1Yei156NisMapLKxUSLDAt1wTS1Q5dv/PXCCsIt1RA9K0AI2QsPrhLVFvicIuVCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"758a7fae465e6dd12b430695d04795eea8a7a4b2eb3be5aa400aabc662d22e08","last_reissued_at":"2026-07-05T11:15:47.361515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:47.361515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24603","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":"2026-07-05T11:15:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6epxrfvcP83PAQNEvdys1gz6NJ0cETIgsk+30zXL4TsO7lF8aF69axfNoM76qdg8AzXwkDB8qEsnhcwES+soCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:42:55.825209Z"},"content_sha256":"e778d4712e7e22d23f95ee1eca66367d03c6d866fbdc87bf31f097eb0e7a3af0","schema_version":"1.0","event_id":"sha256:e778d4712e7e22d23f95ee1eca66367d03c6d866fbdc87bf31f097eb0e7a3af0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OWFH7LSGLZW5CK2DA2K5AR4V52","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Gaussian Mixing Mechanism: Renyi Differential Privacy via Gaussian Sketches","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ashia C. Wilson, Ayush Sekhari, Katrina Ligett, Moshe Shenfeld, Omri Lev, Vishwak Srinivasan","submitted_at":"2025-05-30T13:52:48Z","abstract_excerpt":"Gaussian sketching, which consists of pre-multiplying the data with a random Gaussian matrix, is a widely used technique for multiple problems in data science and machine learning, with applications spanning computationally efficient optimization, coded computing, and federated learning. This operation also provides differential privacy guarantees due to its inherent randomness. In this work, we revisit this operation through the lens of Renyi Differential Privacy (RDP), providing a refined privacy analysis that yields significantly tighter bounds than prior results. We then demonstrate how th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24603","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/2505.24603/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":"2026-07-05T11:15:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wDKP6+neaTIOntPB5ApV9tnbNwCeBI6oz3ljNMY2j2gvGUS1MDQAfdWA/TAKz82zNTUr2OCmROz8vaURZQAWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:42:55.825594Z"},"content_sha256":"846e0e0f4be1bf2ad92229e8b0cde265bca3e2e4b59909d07bf5271fb7e80600","schema_version":"1.0","event_id":"sha256:846e0e0f4be1bf2ad92229e8b0cde265bca3e2e4b59909d07bf5271fb7e80600"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OWFH7LSGLZW5CK2DA2K5AR4V52/bundle.json","state_url":"https://pith.science/pith/OWFH7LSGLZW5CK2DA2K5AR4V52/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OWFH7LSGLZW5CK2DA2K5AR4V52/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":"2026-08-07T20:42:55Z","links":{"resolver":"https://pith.science/pith/OWFH7LSGLZW5CK2DA2K5AR4V52","bundle":"https://pith.science/pith/OWFH7LSGLZW5CK2DA2K5AR4V52/bundle.json","state":"https://pith.science/pith/OWFH7LSGLZW5CK2DA2K5AR4V52/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OWFH7LSGLZW5CK2DA2K5AR4V52/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OWFH7LSGLZW5CK2DA2K5AR4V52","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":"29b39d7e2151625261bc224be22ccade109402fb6710974531438525cbeaf503","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T13:52:48Z","title_canon_sha256":"88bf34186061318d89dbc2bb06c5d4c0fb323e0518bf702238b7bacb135cfd09"},"schema_version":"1.0","source":{"id":"2505.24603","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24603","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24603v2","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24603","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_12","alias_value":"OWFH7LSGLZW5","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_16","alias_value":"OWFH7LSGLZW5CK2D","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_8","alias_value":"OWFH7LSG","created_at":"2026-07-05T11:15:47Z"}],"graph_snapshots":[{"event_id":"sha256:846e0e0f4be1bf2ad92229e8b0cde265bca3e2e4b59909d07bf5271fb7e80600","target":"graph","created_at":"2026-07-05T11:15:47Z","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/2505.24603/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gaussian sketching, which consists of pre-multiplying the data with a random Gaussian matrix, is a widely used technique for multiple problems in data science and machine learning, with applications spanning computationally efficient optimization, coded computing, and federated learning. This operation also provides differential privacy guarantees due to its inherent randomness. In this work, we revisit this operation through the lens of Renyi Differential Privacy (RDP), providing a refined privacy analysis that yields significantly tighter bounds than prior results. We then demonstrate how th","authors_text":"Ashia C. Wilson, Ayush Sekhari, Katrina Ligett, Moshe Shenfeld, Omri Lev, Vishwak Srinivasan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T13:52:48Z","title":"The Gaussian Mixing Mechanism: Renyi Differential Privacy via Gaussian Sketches"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24603","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:e778d4712e7e22d23f95ee1eca66367d03c6d866fbdc87bf31f097eb0e7a3af0","target":"record","created_at":"2026-07-05T11:15:47Z","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":"29b39d7e2151625261bc224be22ccade109402fb6710974531438525cbeaf503","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T13:52:48Z","title_canon_sha256":"88bf34186061318d89dbc2bb06c5d4c0fb323e0518bf702238b7bacb135cfd09"},"schema_version":"1.0","source":{"id":"2505.24603","kind":"arxiv","version":2}},"canonical_sha256":"758a7fae465e6dd12b430695d04795eea8a7a4b2eb3be5aa400aabc662d22e08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"758a7fae465e6dd12b430695d04795eea8a7a4b2eb3be5aa400aabc662d22e08","first_computed_at":"2026-07-05T11:15:47.361515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:47.361515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b29M3g1jFF124dfWvGqai1Yei156NisMapLKxUSLDAt1wTS1Q5dv/PXCCsIt1RA9K0AI2QsPrhLVFvicIuVCCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:47.362063Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24603","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e778d4712e7e22d23f95ee1eca66367d03c6d866fbdc87bf31f097eb0e7a3af0","sha256:846e0e0f4be1bf2ad92229e8b0cde265bca3e2e4b59909d07bf5271fb7e80600"],"state_sha256":"34a644fb05cc47d840543ff1cb46ea7176bd83cf5c047730deb0f7aba00a2015"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E+00MBz57D0vtRjaIdFXoZhQKXE1H0HR9PdCLaihxI5pL/7wF3uDwku1BWDqu0HxlJmfLcDH95Z6Fx7/B9WRCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T20:42:55.828628Z","bundle_sha256":"29b852530cc61294c2214ae8824a9f1430fbecacae6d11ce5985167d8ff14f8e"}}