{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KF7UC5HE62P6P6TIWSUPRKNPL4","short_pith_number":"pith:KF7UC5HE","schema_version":"1.0","canonical_sha256":"517f4174e4f69fe7fa68b4a8f8a9af5f38b90fa540d3658daa3562ec39b19578","source":{"kind":"arxiv","id":"2202.02575","version":2},"attestation_state":"computed","paper":{"title":"Differentially Private Graph Classification with GNNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Chinmay Prabhakar, Daniel Rueckert, Dmitrii Usynin, Georgios Kaissis, Johannes C. Paetzold, Tamara T. Mueller","submitted_at":"2022-02-05T15:16:40Z","abstract_excerpt":"Graph Neural Networks (GNNs) have established themselves as the state-of-the-art models for many machine learning applications such as the analysis of social networks, protein interactions and molecules. Several among these datasets contain privacy-sensitive data. Machine learning with differential privacy is a promising technique to allow deriving insight from sensitive data while offering formal guarantees of privacy protection. However, the differentially private training of GNNs has so far remained under-explored due to the challenges presented by the intrinsic structural connectivity of g"},"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":"2202.02575","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-05T15:16:40Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"1ceb81e29e49139c952855e2b9ab8c2b90344161c5623cad51604d8f74990921","abstract_canon_sha256":"859c35a4a256cfbe6b9b389943e116079893060832185da184340e4523ed220a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:24.282851Z","signature_b64":"gaQCMQaz4RcQuwj31eHxX1UjGur0kJKdhsFkzlmBGd+L56qOHEFLvyP0L2ayYCh4l9cCs6TM/q5xf4NtAcI6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"517f4174e4f69fe7fa68b4a8f8a9af5f38b90fa540d3658daa3562ec39b19578","last_reissued_at":"2026-07-05T06:30:24.282296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:24.282296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentially Private Graph Classification with GNNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Chinmay Prabhakar, Daniel Rueckert, Dmitrii Usynin, Georgios Kaissis, Johannes C. Paetzold, Tamara T. Mueller","submitted_at":"2022-02-05T15:16:40Z","abstract_excerpt":"Graph Neural Networks (GNNs) have established themselves as the state-of-the-art models for many machine learning applications such as the analysis of social networks, protein interactions and molecules. Several among these datasets contain privacy-sensitive data. Machine learning with differential privacy is a promising technique to allow deriving insight from sensitive data while offering formal guarantees of privacy protection. However, the differentially private training of GNNs has so far remained under-explored due to the challenges presented by the intrinsic structural connectivity of g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.02575","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/2202.02575/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":"2202.02575","created_at":"2026-07-05T06:30:24.282365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.02575v2","created_at":"2026-07-05T06:30:24.282365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.02575","created_at":"2026-07-05T06:30:24.282365+00:00"},{"alias_kind":"pith_short_12","alias_value":"KF7UC5HE62P6","created_at":"2026-07-05T06:30:24.282365+00:00"},{"alias_kind":"pith_short_16","alias_value":"KF7UC5HE62P6P6TI","created_at":"2026-07-05T06:30:24.282365+00:00"},{"alias_kind":"pith_short_8","alias_value":"KF7UC5HE","created_at":"2026-07-05T06:30:24.282365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KF7UC5HE62P6P6TIWSUPRKNPL4","json":"https://pith.science/pith/KF7UC5HE62P6P6TIWSUPRKNPL4.json","graph_json":"https://pith.science/api/pith-number/KF7UC5HE62P6P6TIWSUPRKNPL4/graph.json","events_json":"https://pith.science/api/pith-number/KF7UC5HE62P6P6TIWSUPRKNPL4/events.json","paper":"https://pith.science/paper/KF7UC5HE"},"agent_actions":{"view_html":"https://pith.science/pith/KF7UC5HE62P6P6TIWSUPRKNPL4","download_json":"https://pith.science/pith/KF7UC5HE62P6P6TIWSUPRKNPL4.json","view_paper":"https://pith.science/paper/KF7UC5HE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.02575&json=true","fetch_graph":"https://pith.science/api/pith-number/KF7UC5HE62P6P6TIWSUPRKNPL4/graph.json","fetch_events":"https://pith.science/api/pith-number/KF7UC5HE62P6P6TIWSUPRKNPL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KF7UC5HE62P6P6TIWSUPRKNPL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KF7UC5HE62P6P6TIWSUPRKNPL4/action/storage_attestation","attest_author":"https://pith.science/pith/KF7UC5HE62P6P6TIWSUPRKNPL4/action/author_attestation","sign_citation":"https://pith.science/pith/KF7UC5HE62P6P6TIWSUPRKNPL4/action/citation_signature","submit_replication":"https://pith.science/pith/KF7UC5HE62P6P6TIWSUPRKNPL4/action/replication_record"}},"created_at":"2026-07-05T06:30:24.282365+00:00","updated_at":"2026-07-05T06:30:24.282365+00:00"}