{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NPL5VUQPMTCHOB7WHKVPYRPTZL","short_pith_number":"pith:NPL5VUQP","schema_version":"1.0","canonical_sha256":"6bd7dad20f64c47707f63aaafc45f3caf38375792cc81e352ce72ae5f383b5f7","source":{"kind":"arxiv","id":"2406.04805","version":3},"attestation_state":"computed","paper":{"title":"GENIE: Watermarking Graph Neural Networks for Link Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Aaryan Ajay Sharma, Ankit Gangwal, Charu Sharma, Venkata Sai Pranav Bachina","submitted_at":"2024-06-07T10:12:01Z","abstract_excerpt":"Graph Neural Networks (GNNs) have become invaluable intellectual property in graph-based machine learning. However, their vulnerability to model stealing attacks when deployed within Machine Learning as a Service (MLaaS) necessitates robust Ownership Demonstration (OD) techniques. Watermarking is a promising OD framework for Deep Neural Networks, but existing methods fail to generalize to GNNs due to the non-Euclidean nature of graph data. Previous works on GNN watermarking have primarily focused on node and graph classification, overlooking Link Prediction (LP).\n  In this paper, we propose GE"},"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":"2406.04805","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-06-07T10:12:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5c0106b73ae3a71387950570309d67a12d82f5d99c29cebf0590c63e866a1077","abstract_canon_sha256":"9deb6bf5ca746aec933d9ff3ea0bf0f0a73db15b2014c0083837d5b4f281edc5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:48.120245Z","signature_b64":"i+07tX1ymkq/79QJFoLB8y1WHZsKPmuCqP/wuZJYX/jufskycot5Mm8KL0hbj9gtwn7rqGpRnT4SQLNG7hJeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bd7dad20f64c47707f63aaafc45f3caf38375792cc81e352ce72ae5f383b5f7","last_reissued_at":"2026-07-05T09:59:48.119812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:48.119812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GENIE: Watermarking Graph Neural Networks for Link Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Aaryan Ajay Sharma, Ankit Gangwal, Charu Sharma, Venkata Sai Pranav Bachina","submitted_at":"2024-06-07T10:12:01Z","abstract_excerpt":"Graph Neural Networks (GNNs) have become invaluable intellectual property in graph-based machine learning. However, their vulnerability to model stealing attacks when deployed within Machine Learning as a Service (MLaaS) necessitates robust Ownership Demonstration (OD) techniques. Watermarking is a promising OD framework for Deep Neural Networks, but existing methods fail to generalize to GNNs due to the non-Euclidean nature of graph data. Previous works on GNN watermarking have primarily focused on node and graph classification, overlooking Link Prediction (LP).\n  In this paper, we propose GE"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04805","kind":"arxiv","version":3},"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/2406.04805/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":"2406.04805","created_at":"2026-07-05T09:59:48.119876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04805v3","created_at":"2026-07-05T09:59:48.119876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04805","created_at":"2026-07-05T09:59:48.119876+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPL5VUQPMTCH","created_at":"2026-07-05T09:59:48.119876+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPL5VUQPMTCHOB7W","created_at":"2026-07-05T09:59:48.119876+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPL5VUQP","created_at":"2026-07-05T09:59:48.119876+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.19641","citing_title":"Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses","ref_index":116,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NPL5VUQPMTCHOB7WHKVPYRPTZL","json":"https://pith.science/pith/NPL5VUQPMTCHOB7WHKVPYRPTZL.json","graph_json":"https://pith.science/api/pith-number/NPL5VUQPMTCHOB7WHKVPYRPTZL/graph.json","events_json":"https://pith.science/api/pith-number/NPL5VUQPMTCHOB7WHKVPYRPTZL/events.json","paper":"https://pith.science/paper/NPL5VUQP"},"agent_actions":{"view_html":"https://pith.science/pith/NPL5VUQPMTCHOB7WHKVPYRPTZL","download_json":"https://pith.science/pith/NPL5VUQPMTCHOB7WHKVPYRPTZL.json","view_paper":"https://pith.science/paper/NPL5VUQP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04805&json=true","fetch_graph":"https://pith.science/api/pith-number/NPL5VUQPMTCHOB7WHKVPYRPTZL/graph.json","fetch_events":"https://pith.science/api/pith-number/NPL5VUQPMTCHOB7WHKVPYRPTZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPL5VUQPMTCHOB7WHKVPYRPTZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPL5VUQPMTCHOB7WHKVPYRPTZL/action/storage_attestation","attest_author":"https://pith.science/pith/NPL5VUQPMTCHOB7WHKVPYRPTZL/action/author_attestation","sign_citation":"https://pith.science/pith/NPL5VUQPMTCHOB7WHKVPYRPTZL/action/citation_signature","submit_replication":"https://pith.science/pith/NPL5VUQPMTCHOB7WHKVPYRPTZL/action/replication_record"}},"created_at":"2026-07-05T09:59:48.119876+00:00","updated_at":"2026-07-05T09:59:48.119876+00:00"}