{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KBSPUCKO3OTUCFYZYYFUAHIJA3","short_pith_number":"pith:KBSPUCKO","schema_version":"1.0","canonical_sha256":"5064fa094edba7411719c60b401d0906f2c3079cc0d09e0d99c2b5e37cea47d0","source":{"kind":"arxiv","id":"2210.13918","version":2},"attestation_state":"computed","paper":{"title":"Differentially Private Language Models for Secure Data Sharing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CR"],"primary_cat":"cs.LG","authors_text":"Benjamin Weggenmann, Bernhard Schoelkopf, Justus Mattern, Mrinmaya Sachan, Zhijing Jin","submitted_at":"2022-10-25T11:12:56Z","abstract_excerpt":"To protect the privacy of individuals whose data is being shared, it is of high importance to develop methods allowing researchers and companies to release textual data while providing formal privacy guarantees to its originators. In the field of NLP, substantial efforts have been directed at building mechanisms following the framework of local differential privacy, thereby anonymizing individual text samples before releasing them. In practice, these approaches are often dissatisfying in terms of the quality of their output language due to the strong noise required for local differential priva"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.13918","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-25T11:12:56Z","cross_cats_sorted":["cs.CL","cs.CR"],"title_canon_sha256":"9ce0ef8814197444f686d4e33a53272afc94d8243c10652d9063946128b69d7c","abstract_canon_sha256":"b58c78bc4d973b0deed9a9356f6891ed054c2b2a65db941dcdec36478f509d35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:42.911533Z","signature_b64":"4J98zg0nf344ZOydXXGKFjWYmVzaAkmGCEIS0hoWG8ooxos9IPkZ6/r0wWfshQq8cIMIlbzOCvR/1AKtJ5OBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5064fa094edba7411719c60b401d0906f2c3079cc0d09e0d99c2b5e37cea47d0","last_reissued_at":"2026-07-05T05:10:42.910936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:42.910936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentially Private Language Models for Secure Data Sharing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CR"],"primary_cat":"cs.LG","authors_text":"Benjamin Weggenmann, Bernhard Schoelkopf, Justus Mattern, Mrinmaya Sachan, Zhijing Jin","submitted_at":"2022-10-25T11:12:56Z","abstract_excerpt":"To protect the privacy of individuals whose data is being shared, it is of high importance to develop methods allowing researchers and companies to release textual data while providing formal privacy guarantees to its originators. In the field of NLP, substantial efforts have been directed at building mechanisms following the framework of local differential privacy, thereby anonymizing individual text samples before releasing them. In practice, these approaches are often dissatisfying in terms of the quality of their output language due to the strong noise required for local differential priva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13918","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/2210.13918/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.13918","created_at":"2026-07-05T05:10:42.911008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.13918v2","created_at":"2026-07-05T05:10:42.911008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13918","created_at":"2026-07-05T05:10:42.911008+00:00"},{"alias_kind":"pith_short_12","alias_value":"KBSPUCKO3OTU","created_at":"2026-07-05T05:10:42.911008+00:00"},{"alias_kind":"pith_short_16","alias_value":"KBSPUCKO3OTUCFYZ","created_at":"2026-07-05T05:10:42.911008+00:00"},{"alias_kind":"pith_short_8","alias_value":"KBSPUCKO","created_at":"2026-07-05T05:10:42.911008+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04461","citing_title":"DP-OPD: Differentially Private On-Policy Distillation for Language Models","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KBSPUCKO3OTUCFYZYYFUAHIJA3","json":"https://pith.science/pith/KBSPUCKO3OTUCFYZYYFUAHIJA3.json","graph_json":"https://pith.science/api/pith-number/KBSPUCKO3OTUCFYZYYFUAHIJA3/graph.json","events_json":"https://pith.science/api/pith-number/KBSPUCKO3OTUCFYZYYFUAHIJA3/events.json","paper":"https://pith.science/paper/KBSPUCKO"},"agent_actions":{"view_html":"https://pith.science/pith/KBSPUCKO3OTUCFYZYYFUAHIJA3","download_json":"https://pith.science/pith/KBSPUCKO3OTUCFYZYYFUAHIJA3.json","view_paper":"https://pith.science/paper/KBSPUCKO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.13918&json=true","fetch_graph":"https://pith.science/api/pith-number/KBSPUCKO3OTUCFYZYYFUAHIJA3/graph.json","fetch_events":"https://pith.science/api/pith-number/KBSPUCKO3OTUCFYZYYFUAHIJA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KBSPUCKO3OTUCFYZYYFUAHIJA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KBSPUCKO3OTUCFYZYYFUAHIJA3/action/storage_attestation","attest_author":"https://pith.science/pith/KBSPUCKO3OTUCFYZYYFUAHIJA3/action/author_attestation","sign_citation":"https://pith.science/pith/KBSPUCKO3OTUCFYZYYFUAHIJA3/action/citation_signature","submit_replication":"https://pith.science/pith/KBSPUCKO3OTUCFYZYYFUAHIJA3/action/replication_record"}},"created_at":"2026-07-05T05:10:42.911008+00:00","updated_at":"2026-07-05T05:10:42.911008+00:00"}