{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VHBL3LPN37STGYIRIK4UHNKR5C","short_pith_number":"pith:VHBL3LPN","schema_version":"1.0","canonical_sha256":"a9c2bdadeddfe533611142b943b551e8aacf81cf3526fcc575620acf69101381","source":{"kind":"arxiv","id":"2105.13418","version":1},"attestation_state":"computed","paper":{"title":"On Privacy and Confidentiality of Communications in Organizational Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CR","authors_text":"Huseyin Inan, Marcello Hasegawa, Masoumeh Shafieinejad, Robert Sim","submitted_at":"2021-05-27T19:45:56Z","abstract_excerpt":"Machine learned models trained on organizational communication data, such as emails in an enterprise, carry unique risks of breaching confidentiality, even if the model is intended only for internal use. This work shows how confidentiality is distinct from privacy in an enterprise context, and aims to formulate an approach to preserving confidentiality while leveraging principles from differential privacy. The goal is to perform machine learning tasks, such as learning a language model or performing topic analysis, using interpersonal communications in the organization, while not learning abou"},"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":"2105.13418","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2021-05-27T19:45:56Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"918182baa07cddf06901e7457aff5b2925d05a3cb730a706e639a4c1c567c190","abstract_canon_sha256":"639d0146270c4ba0052ebdd470959286900af1c71644e5ee6168c88923bafd14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:07.734227Z","signature_b64":"/UP+1NCZTlUUgv8L/GTG33C9lWotob+JbzM1fkqcpPWjhNKs6eWTjvx7b1VIu/qqJk1Ijlu1iNsWDM0yeLDtBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9c2bdadeddfe533611142b943b551e8aacf81cf3526fcc575620acf69101381","last_reissued_at":"2026-07-05T02:44:07.733738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:07.733738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Privacy and Confidentiality of Communications in Organizational Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CR","authors_text":"Huseyin Inan, Marcello Hasegawa, Masoumeh Shafieinejad, Robert Sim","submitted_at":"2021-05-27T19:45:56Z","abstract_excerpt":"Machine learned models trained on organizational communication data, such as emails in an enterprise, carry unique risks of breaching confidentiality, even if the model is intended only for internal use. This work shows how confidentiality is distinct from privacy in an enterprise context, and aims to formulate an approach to preserving confidentiality while leveraging principles from differential privacy. The goal is to perform machine learning tasks, such as learning a language model or performing topic analysis, using interpersonal communications in the organization, while not learning abou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13418","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/2105.13418/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":"2105.13418","created_at":"2026-07-05T02:44:07.733792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.13418v1","created_at":"2026-07-05T02:44:07.733792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13418","created_at":"2026-07-05T02:44:07.733792+00:00"},{"alias_kind":"pith_short_12","alias_value":"VHBL3LPN37ST","created_at":"2026-07-05T02:44:07.733792+00:00"},{"alias_kind":"pith_short_16","alias_value":"VHBL3LPN37STGYIR","created_at":"2026-07-05T02:44:07.733792+00:00"},{"alias_kind":"pith_short_8","alias_value":"VHBL3LPN","created_at":"2026-07-05T02:44:07.733792+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.18779","citing_title":"SoK: Practical Aspects of Releasing Differentially Private Graphs","ref_index":141,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VHBL3LPN37STGYIRIK4UHNKR5C","json":"https://pith.science/pith/VHBL3LPN37STGYIRIK4UHNKR5C.json","graph_json":"https://pith.science/api/pith-number/VHBL3LPN37STGYIRIK4UHNKR5C/graph.json","events_json":"https://pith.science/api/pith-number/VHBL3LPN37STGYIRIK4UHNKR5C/events.json","paper":"https://pith.science/paper/VHBL3LPN"},"agent_actions":{"view_html":"https://pith.science/pith/VHBL3LPN37STGYIRIK4UHNKR5C","download_json":"https://pith.science/pith/VHBL3LPN37STGYIRIK4UHNKR5C.json","view_paper":"https://pith.science/paper/VHBL3LPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.13418&json=true","fetch_graph":"https://pith.science/api/pith-number/VHBL3LPN37STGYIRIK4UHNKR5C/graph.json","fetch_events":"https://pith.science/api/pith-number/VHBL3LPN37STGYIRIK4UHNKR5C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VHBL3LPN37STGYIRIK4UHNKR5C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VHBL3LPN37STGYIRIK4UHNKR5C/action/storage_attestation","attest_author":"https://pith.science/pith/VHBL3LPN37STGYIRIK4UHNKR5C/action/author_attestation","sign_citation":"https://pith.science/pith/VHBL3LPN37STGYIRIK4UHNKR5C/action/citation_signature","submit_replication":"https://pith.science/pith/VHBL3LPN37STGYIRIK4UHNKR5C/action/replication_record"}},"created_at":"2026-07-05T02:44:07.733792+00:00","updated_at":"2026-07-05T02:44:07.733792+00:00"}