{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3TNRBAOFZYBL2ITDOXW6VC3NI2","short_pith_number":"pith:3TNRBAOF","schema_version":"1.0","canonical_sha256":"dcdb1081c5ce02bd226375edea8b6d4696207af8c242e32dd5c22dd3ca600ea3","source":{"kind":"arxiv","id":"2107.07928","version":1},"attestation_state":"computed","paper":{"title":"TEM: High Utility Metric Differential Privacy on Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Oluwaseyi Feyisetan, Ricardo Silva Carvalho, Theodore Vasiloudis","submitted_at":"2021-07-16T14:38:16Z","abstract_excerpt":"Ensuring the privacy of users whose data are used to train Natural Language Processing (NLP) models is necessary to build and maintain customer trust. Differential Privacy (DP) has emerged as the most successful method to protect the privacy of individuals. However, applying DP to the NLP domain comes with unique challenges. The most successful previous methods use a generalization of DP for metric spaces, and apply the privatization by adding noise to inputs in the metric space of word embeddings. However, these methods assume that one specific distance measure is being used, ignore the densi"},"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":"2107.07928","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2021-07-16T14:38:16Z","cross_cats_sorted":[],"title_canon_sha256":"df43e93c6670cdd07e5303d527afd953c71eac9144a95ca606f1bb799c41fa10","abstract_canon_sha256":"f3fe543b432bc1a9c596360b2417957d499e1580561590cd12386104c74b6ee5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:30.522180Z","signature_b64":"4z7cEum+9p4uBNIqW2CLAf7rTYAlgR4wyAnpOmrUnglDMdXfAu12nrHKoNy50kcvBV0PPjf1Abq4YU5XYyHCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcdb1081c5ce02bd226375edea8b6d4696207af8c242e32dd5c22dd3ca600ea3","last_reissued_at":"2026-07-05T02:58:30.521823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:30.521823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TEM: High Utility Metric Differential Privacy on Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Oluwaseyi Feyisetan, Ricardo Silva Carvalho, Theodore Vasiloudis","submitted_at":"2021-07-16T14:38:16Z","abstract_excerpt":"Ensuring the privacy of users whose data are used to train Natural Language Processing (NLP) models is necessary to build and maintain customer trust. Differential Privacy (DP) has emerged as the most successful method to protect the privacy of individuals. However, applying DP to the NLP domain comes with unique challenges. The most successful previous methods use a generalization of DP for metric spaces, and apply the privatization by adding noise to inputs in the metric space of word embeddings. However, these methods assume that one specific distance measure is being used, ignore the densi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.07928","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/2107.07928/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":"2107.07928","created_at":"2026-07-05T02:58:30.521878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.07928v1","created_at":"2026-07-05T02:58:30.521878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.07928","created_at":"2026-07-05T02:58:30.521878+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TNRBAOFZYBL","created_at":"2026-07-05T02:58:30.521878+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TNRBAOFZYBL2ITD","created_at":"2026-07-05T02:58:30.521878+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TNRBAOF","created_at":"2026-07-05T02:58:30.521878+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26351","citing_title":"Context-Aware Metric Differential Privacy for Vehicle Trajectory Data","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3TNRBAOFZYBL2ITDOXW6VC3NI2","json":"https://pith.science/pith/3TNRBAOFZYBL2ITDOXW6VC3NI2.json","graph_json":"https://pith.science/api/pith-number/3TNRBAOFZYBL2ITDOXW6VC3NI2/graph.json","events_json":"https://pith.science/api/pith-number/3TNRBAOFZYBL2ITDOXW6VC3NI2/events.json","paper":"https://pith.science/paper/3TNRBAOF"},"agent_actions":{"view_html":"https://pith.science/pith/3TNRBAOFZYBL2ITDOXW6VC3NI2","download_json":"https://pith.science/pith/3TNRBAOFZYBL2ITDOXW6VC3NI2.json","view_paper":"https://pith.science/paper/3TNRBAOF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.07928&json=true","fetch_graph":"https://pith.science/api/pith-number/3TNRBAOFZYBL2ITDOXW6VC3NI2/graph.json","fetch_events":"https://pith.science/api/pith-number/3TNRBAOFZYBL2ITDOXW6VC3NI2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TNRBAOFZYBL2ITDOXW6VC3NI2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TNRBAOFZYBL2ITDOXW6VC3NI2/action/storage_attestation","attest_author":"https://pith.science/pith/3TNRBAOFZYBL2ITDOXW6VC3NI2/action/author_attestation","sign_citation":"https://pith.science/pith/3TNRBAOFZYBL2ITDOXW6VC3NI2/action/citation_signature","submit_replication":"https://pith.science/pith/3TNRBAOFZYBL2ITDOXW6VC3NI2/action/replication_record"}},"created_at":"2026-07-05T02:58:30.521878+00:00","updated_at":"2026-07-05T02:58:30.521878+00:00"}