{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OS5IANCKEZUSYBB74NEPKDUIXP","short_pith_number":"pith:OS5IANCK","canonical_record":{"source":{"id":"2403.01749","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T05:57:50Z","cross_cats_sorted":[],"title_canon_sha256":"50762934a4bb1aa692e41967f5a6fdb9b6131a3e0ef607a40eb8857fdb0bdb77","abstract_canon_sha256":"5b7f61f72fbe11d60bfa6c63b33c3378725c637db8a7cce442ac4d579a62b20c"},"schema_version":"1.0"},"canonical_sha256":"74ba80344a26692c043fe348f50e88bbf8f12d78978a77da3a09a18fcc9c6584","source":{"kind":"arxiv","id":"2403.01749","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01749","created_at":"2026-07-05T08:47:50Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01749v2","created_at":"2026-07-05T08:47:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01749","created_at":"2026-07-05T08:47:50Z"},{"alias_kind":"pith_short_12","alias_value":"OS5IANCKEZUS","created_at":"2026-07-05T08:47:50Z"},{"alias_kind":"pith_short_16","alias_value":"OS5IANCKEZUSYBB7","created_at":"2026-07-05T08:47:50Z"},{"alias_kind":"pith_short_8","alias_value":"OS5IANCK","created_at":"2026-07-05T08:47:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OS5IANCKEZUSYBB74NEPKDUIXP","target":"record","payload":{"canonical_record":{"source":{"id":"2403.01749","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T05:57:50Z","cross_cats_sorted":[],"title_canon_sha256":"50762934a4bb1aa692e41967f5a6fdb9b6131a3e0ef607a40eb8857fdb0bdb77","abstract_canon_sha256":"5b7f61f72fbe11d60bfa6c63b33c3378725c637db8a7cce442ac4d579a62b20c"},"schema_version":"1.0"},"canonical_sha256":"74ba80344a26692c043fe348f50e88bbf8f12d78978a77da3a09a18fcc9c6584","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:50.599889Z","signature_b64":"qVCgiAeaqO8nCicxO5Le+tT9X7J6rSX3aojlwfUeYXF/ig4t7bJmJRwg0Cl39NmtUbCecHPGRw2oAKx1Goh8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74ba80344a26692c043fe348f50e88bbf8f12d78978a77da3a09a18fcc9c6584","last_reissued_at":"2026-07-05T08:47:50.599338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:50.599338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.01749","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":"2026-07-05T08:47:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mSKyNAZM3OZ1WhYnXaIP0lOEODYZZWaLFMSvkWGE6JGhLjFcPT3dt2gKA2M74f65cjUUwSKo69nbbRydeZ3VBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:19:34.920118Z"},"content_sha256":"149bae5b3b4cada89565cfa9221c02903776f1cf2009428bb980652d4ea1b897","schema_version":"1.0","event_id":"sha256:149bae5b3b4cada89565cfa9221c02903776f1cf2009428bb980652d4ea1b897"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OS5IANCKEZUSYBB74NEPKDUIXP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arturs Backurs, Bo Li, Chulin Xie, Da Yu, Haotian Jiang, Harsha Nori, Huishuai Zhang, Huseyin A Inan, Sergey Yekhanin, Sivakanth Gopi, Yin Tat Lee, Zinan Lin","submitted_at":"2024-03-04T05:57:50Z","abstract_excerpt":"Text data has become extremely valuable due to the emergence of machine learning algorithms that learn from it. A lot of high-quality text data generated in the real world is private and therefore cannot be shared or used freely due to privacy concerns. Generating synthetic replicas of private text data with a formal privacy guarantee, i.e., differential privacy (DP), offers a promising and scalable solution. However, existing methods necessitate DP finetuning of large language models (LLMs) on private data to generate DP synthetic data. This approach is not viable for proprietary LLMs (e.g., "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01749","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/2403.01749/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":"2026-07-05T08:47:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YhYf5syPFH8nfRCHcBrG94CcazLZhbgj0Du5zfQWPnRxXM2vDaxxcYRAHAEKRDJE3mM0IPnNVvpUZjz4zxOgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:19:34.920514Z"},"content_sha256":"cd42500003662a992745d1a6c72738c7e5f1c63db1a0efed8ce33200dd11867b","schema_version":"1.0","event_id":"sha256:cd42500003662a992745d1a6c72738c7e5f1c63db1a0efed8ce33200dd11867b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OS5IANCKEZUSYBB74NEPKDUIXP/bundle.json","state_url":"https://pith.science/pith/OS5IANCKEZUSYBB74NEPKDUIXP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OS5IANCKEZUSYBB74NEPKDUIXP/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":"2026-07-06T23:19:34Z","links":{"resolver":"https://pith.science/pith/OS5IANCKEZUSYBB74NEPKDUIXP","bundle":"https://pith.science/pith/OS5IANCKEZUSYBB74NEPKDUIXP/bundle.json","state":"https://pith.science/pith/OS5IANCKEZUSYBB74NEPKDUIXP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OS5IANCKEZUSYBB74NEPKDUIXP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OS5IANCKEZUSYBB74NEPKDUIXP","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":"5b7f61f72fbe11d60bfa6c63b33c3378725c637db8a7cce442ac4d579a62b20c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T05:57:50Z","title_canon_sha256":"50762934a4bb1aa692e41967f5a6fdb9b6131a3e0ef607a40eb8857fdb0bdb77"},"schema_version":"1.0","source":{"id":"2403.01749","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01749","created_at":"2026-07-05T08:47:50Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01749v2","created_at":"2026-07-05T08:47:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01749","created_at":"2026-07-05T08:47:50Z"},{"alias_kind":"pith_short_12","alias_value":"OS5IANCKEZUS","created_at":"2026-07-05T08:47:50Z"},{"alias_kind":"pith_short_16","alias_value":"OS5IANCKEZUSYBB7","created_at":"2026-07-05T08:47:50Z"},{"alias_kind":"pith_short_8","alias_value":"OS5IANCK","created_at":"2026-07-05T08:47:50Z"}],"graph_snapshots":[{"event_id":"sha256:cd42500003662a992745d1a6c72738c7e5f1c63db1a0efed8ce33200dd11867b","target":"graph","created_at":"2026-07-05T08:47:50Z","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/2403.01749/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text data has become extremely valuable due to the emergence of machine learning algorithms that learn from it. A lot of high-quality text data generated in the real world is private and therefore cannot be shared or used freely due to privacy concerns. Generating synthetic replicas of private text data with a formal privacy guarantee, i.e., differential privacy (DP), offers a promising and scalable solution. However, existing methods necessitate DP finetuning of large language models (LLMs) on private data to generate DP synthetic data. This approach is not viable for proprietary LLMs (e.g., ","authors_text":"Arturs Backurs, Bo Li, Chulin Xie, Da Yu, Haotian Jiang, Harsha Nori, Huishuai Zhang, Huseyin A Inan, Sergey Yekhanin, Sivakanth Gopi, Yin Tat Lee, Zinan Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T05:57:50Z","title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01749","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":"sha256:149bae5b3b4cada89565cfa9221c02903776f1cf2009428bb980652d4ea1b897","target":"record","created_at":"2026-07-05T08:47:50Z","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":"5b7f61f72fbe11d60bfa6c63b33c3378725c637db8a7cce442ac4d579a62b20c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T05:57:50Z","title_canon_sha256":"50762934a4bb1aa692e41967f5a6fdb9b6131a3e0ef607a40eb8857fdb0bdb77"},"schema_version":"1.0","source":{"id":"2403.01749","kind":"arxiv","version":2}},"canonical_sha256":"74ba80344a26692c043fe348f50e88bbf8f12d78978a77da3a09a18fcc9c6584","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74ba80344a26692c043fe348f50e88bbf8f12d78978a77da3a09a18fcc9c6584","first_computed_at":"2026-07-05T08:47:50.599338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:47:50.599338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qVCgiAeaqO8nCicxO5Le+tT9X7J6rSX3aojlwfUeYXF/ig4t7bJmJRwg0Cl39NmtUbCecHPGRw2oAKx1Goh8Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:47:50.599889Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.01749","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:149bae5b3b4cada89565cfa9221c02903776f1cf2009428bb980652d4ea1b897","sha256:cd42500003662a992745d1a6c72738c7e5f1c63db1a0efed8ce33200dd11867b"],"state_sha256":"a1648c89f725b1d23320a6f5dde9db19a68bb3c3fdd230384887c0f5df22d43e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Z1oZvPQ6ZUGV9wGr1jCUyEtSakYkhZVxgfPIIDZjAVe+rmlQpLiiZ4JKSo9DMmrxQcUKytosrwvHBtx0+J9Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:19:34.922538Z","bundle_sha256":"119db32e3645209cab6e4b74dfde0de66c9e9f470cea9e2b0084663608542d8f"}}