{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SA7VUJM6FR5YPFWYZHHFPEHVJZ","short_pith_number":"pith:SA7VUJM6","schema_version":"1.0","canonical_sha256":"903f5a259e2c7b8796d8c9ce5790f54e7f0bd11ed6257e9b6eb89427b44b78c6","source":{"kind":"arxiv","id":"2311.14465","version":2},"attestation_state":"computed","paper":{"title":"DP-NMT: Scalable Differentially-Private Machine Translation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Doan Nam Long Vu, Felix K\\\"unnecke, Ivan Habernal, Jannik Holmer, Timour Igamberdiev, Zhuo Yu","submitted_at":"2023-11-24T13:19:47Z","abstract_excerpt":"Neural machine translation (NMT) is a widely popular text generation task, yet there is a considerable research gap in the development of privacy-preserving NMT models, despite significant data privacy concerns for NMT systems. Differentially private stochastic gradient descent (DP-SGD) is a popular method for training machine learning models with concrete privacy guarantees; however, the implementation specifics of training a model with DP-SGD are not always clarified in existing models, with differing software libraries used and code bases not always being public, leading to reproducibility "},"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":"2311.14465","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-24T13:19:47Z","cross_cats_sorted":[],"title_canon_sha256":"2b6582962c0ad8a8c203748b8c02f158e986e2311049137279b560d1b7e376ab","abstract_canon_sha256":"a099a716e38b579ef9ae03beff1be7aeb144f77025f8984b04472b8e78f0cd6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:42.179237Z","signature_b64":"RuFl3+yLo+KeDPR0EqnLBtUwZYlz3euCm9TCovdHQAATlOEflYvG+UGOzxQWykSS3sND2BadzvLPU9+DGhwLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"903f5a259e2c7b8796d8c9ce5790f54e7f0bd11ed6257e9b6eb89427b44b78c6","last_reissued_at":"2026-07-05T08:11:42.178759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:42.178759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DP-NMT: Scalable Differentially-Private Machine Translation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Doan Nam Long Vu, Felix K\\\"unnecke, Ivan Habernal, Jannik Holmer, Timour Igamberdiev, Zhuo Yu","submitted_at":"2023-11-24T13:19:47Z","abstract_excerpt":"Neural machine translation (NMT) is a widely popular text generation task, yet there is a considerable research gap in the development of privacy-preserving NMT models, despite significant data privacy concerns for NMT systems. Differentially private stochastic gradient descent (DP-SGD) is a popular method for training machine learning models with concrete privacy guarantees; however, the implementation specifics of training a model with DP-SGD are not always clarified in existing models, with differing software libraries used and code bases not always being public, leading to reproducibility "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14465","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/2311.14465/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":"2311.14465","created_at":"2026-07-05T08:11:42.178815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.14465v2","created_at":"2026-07-05T08:11:42.178815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14465","created_at":"2026-07-05T08:11:42.178815+00:00"},{"alias_kind":"pith_short_12","alias_value":"SA7VUJM6FR5Y","created_at":"2026-07-05T08:11:42.178815+00:00"},{"alias_kind":"pith_short_16","alias_value":"SA7VUJM6FR5YPFWY","created_at":"2026-07-05T08:11:42.178815+00:00"},{"alias_kind":"pith_short_8","alias_value":"SA7VUJM6","created_at":"2026-07-05T08:11:42.178815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.10237","citing_title":"Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SA7VUJM6FR5YPFWYZHHFPEHVJZ","json":"https://pith.science/pith/SA7VUJM6FR5YPFWYZHHFPEHVJZ.json","graph_json":"https://pith.science/api/pith-number/SA7VUJM6FR5YPFWYZHHFPEHVJZ/graph.json","events_json":"https://pith.science/api/pith-number/SA7VUJM6FR5YPFWYZHHFPEHVJZ/events.json","paper":"https://pith.science/paper/SA7VUJM6"},"agent_actions":{"view_html":"https://pith.science/pith/SA7VUJM6FR5YPFWYZHHFPEHVJZ","download_json":"https://pith.science/pith/SA7VUJM6FR5YPFWYZHHFPEHVJZ.json","view_paper":"https://pith.science/paper/SA7VUJM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.14465&json=true","fetch_graph":"https://pith.science/api/pith-number/SA7VUJM6FR5YPFWYZHHFPEHVJZ/graph.json","fetch_events":"https://pith.science/api/pith-number/SA7VUJM6FR5YPFWYZHHFPEHVJZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SA7VUJM6FR5YPFWYZHHFPEHVJZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SA7VUJM6FR5YPFWYZHHFPEHVJZ/action/storage_attestation","attest_author":"https://pith.science/pith/SA7VUJM6FR5YPFWYZHHFPEHVJZ/action/author_attestation","sign_citation":"https://pith.science/pith/SA7VUJM6FR5YPFWYZHHFPEHVJZ/action/citation_signature","submit_replication":"https://pith.science/pith/SA7VUJM6FR5YPFWYZHHFPEHVJZ/action/replication_record"}},"created_at":"2026-07-05T08:11:42.178815+00:00","updated_at":"2026-07-05T08:11:42.178815+00:00"}