{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GUCISY3U36MQDRPKDEJ4LCPX5L","short_pith_number":"pith:GUCISY3U","schema_version":"1.0","canonical_sha256":"3504896374df9901c5ea1913c589f7eacca6b77223af40c7ae082acaa57151d9","source":{"kind":"arxiv","id":"2601.17130","version":2},"attestation_state":"computed","paper":{"title":"Impact of Graph Structure on Membership-Inference Risk for Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Megha Khosla","submitted_at":"2026-01-23T19:08:36Z","abstract_excerpt":"Graph neural networks (GNNs) are widely used for tasks such as node classification and link prediction, but their use in sensitive settings raises concerns about training-data leakage. Prior work on privacy leakage in GNNs largely borrows assumptions from non-graph domains, overlooking the role of graph structure. We argue for a graph-specific analysis of privacy risk and study how graph structure affects node-level membership inference. We formalize membership inference (MI) over node-neighborhood tuples and investigate two important dimensions: (i) training-graph construction and (ii) infere"},"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":"2601.17130","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-23T19:08:36Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"32d7dfc877d888fcd11384a172a3918ee17b7f343194ccf883993e350d58d196","abstract_canon_sha256":"52f75e42646ab42647f1582e1383471119ccf0873189db30aa6b83e9f89ee9d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:48.046488Z","signature_b64":"xONYkiYbYx3BMXhj8PVypzuX5fnz2mMtiJzTl9EyzbJ+EULe+fUUCI3apo2SbR7qfA5t9SgCqm/HvBi5tLSuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3504896374df9901c5ea1913c589f7eacca6b77223af40c7ae082acaa57151d9","last_reissued_at":"2026-06-03T01:05:48.045996Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:48.045996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Impact of Graph Structure on Membership-Inference Risk for Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Megha Khosla","submitted_at":"2026-01-23T19:08:36Z","abstract_excerpt":"Graph neural networks (GNNs) are widely used for tasks such as node classification and link prediction, but their use in sensitive settings raises concerns about training-data leakage. Prior work on privacy leakage in GNNs largely borrows assumptions from non-graph domains, overlooking the role of graph structure. We argue for a graph-specific analysis of privacy risk and study how graph structure affects node-level membership inference. We formalize membership inference (MI) over node-neighborhood tuples and investigate two important dimensions: (i) training-graph construction and (ii) infere"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.17130","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/2601.17130/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":"2601.17130","created_at":"2026-06-03T01:05:48.046054+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.17130v2","created_at":"2026-06-03T01:05:48.046054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.17130","created_at":"2026-06-03T01:05:48.046054+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUCISY3U36MQ","created_at":"2026-06-03T01:05:48.046054+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUCISY3U36MQDRPK","created_at":"2026-06-03T01:05:48.046054+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUCISY3U","created_at":"2026-06-03T01:05:48.046054+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/GUCISY3U36MQDRPKDEJ4LCPX5L","json":"https://pith.science/pith/GUCISY3U36MQDRPKDEJ4LCPX5L.json","graph_json":"https://pith.science/api/pith-number/GUCISY3U36MQDRPKDEJ4LCPX5L/graph.json","events_json":"https://pith.science/api/pith-number/GUCISY3U36MQDRPKDEJ4LCPX5L/events.json","paper":"https://pith.science/paper/GUCISY3U"},"agent_actions":{"view_html":"https://pith.science/pith/GUCISY3U36MQDRPKDEJ4LCPX5L","download_json":"https://pith.science/pith/GUCISY3U36MQDRPKDEJ4LCPX5L.json","view_paper":"https://pith.science/paper/GUCISY3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.17130&json=true","fetch_graph":"https://pith.science/api/pith-number/GUCISY3U36MQDRPKDEJ4LCPX5L/graph.json","fetch_events":"https://pith.science/api/pith-number/GUCISY3U36MQDRPKDEJ4LCPX5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUCISY3U36MQDRPKDEJ4LCPX5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUCISY3U36MQDRPKDEJ4LCPX5L/action/storage_attestation","attest_author":"https://pith.science/pith/GUCISY3U36MQDRPKDEJ4LCPX5L/action/author_attestation","sign_citation":"https://pith.science/pith/GUCISY3U36MQDRPKDEJ4LCPX5L/action/citation_signature","submit_replication":"https://pith.science/pith/GUCISY3U36MQDRPKDEJ4LCPX5L/action/replication_record"}},"created_at":"2026-06-03T01:05:48.046054+00:00","updated_at":"2026-06-03T01:05:48.046054+00:00"}