{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:X3EMC6F7ZCSMRGGQ3LQ2DZBXHZ","short_pith_number":"pith:X3EMC6F7","schema_version":"1.0","canonical_sha256":"bec8c178bfc8a4c898d0dae1a1e4373e66bc652ecaa58ab26b99330e637a5664","source":{"kind":"arxiv","id":"1909.06543","version":1},"attestation_state":"computed","paper":{"title":"Node Injection Attacks on Graphs via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Suhang Wang, Tsung-Yu Hsieh, Vasant Honavar, Xianfeng Tang, Yiwei Sun","submitted_at":"2019-09-14T06:35:22Z","abstract_excerpt":"Real-world graph applications, such as advertisements and product recommendations make profits based on accurately classify the label of the nodes. However, in such scenarios, there are high incentives for the adversaries to attack such graph to reduce the node classification performance. Previous work on graph adversarial attacks focus on modifying existing graph structures, which is infeasible in most real-world applications. In contrast, it is more practical to inject adversarial nodes into existing graphs, which can also potentially reduce the performance of the classifier. In this paper, "},"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":"1909.06543","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-14T06:35:22Z","cross_cats_sorted":["cs.CR","cs.SI","stat.ML"],"title_canon_sha256":"f64c43697763fef97d59b320af2bbfd5fde46a9cdc3dc128cec349b33a4fc721","abstract_canon_sha256":"57d8d97f5e9530331fad437fc1f75ad03123ab3be8c073bc805d3aed0e4faf2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:47.317094Z","signature_b64":"fimh8GH/HiPnin60+9QqiYpIQILcAM5kVU8enAcMYZrabg1FSDVZZLjk8fKJBW6t5taOMZMjvAm2JJWePhOQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bec8c178bfc8a4c898d0dae1a1e4373e66bc652ecaa58ab26b99330e637a5664","last_reissued_at":"2026-07-05T00:04:47.316699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:47.316699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Node Injection Attacks on Graphs via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Suhang Wang, Tsung-Yu Hsieh, Vasant Honavar, Xianfeng Tang, Yiwei Sun","submitted_at":"2019-09-14T06:35:22Z","abstract_excerpt":"Real-world graph applications, such as advertisements and product recommendations make profits based on accurately classify the label of the nodes. However, in such scenarios, there are high incentives for the adversaries to attack such graph to reduce the node classification performance. Previous work on graph adversarial attacks focus on modifying existing graph structures, which is infeasible in most real-world applications. In contrast, it is more practical to inject adversarial nodes into existing graphs, which can also potentially reduce the performance of the classifier. In this paper, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.06543","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/1909.06543/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":"1909.06543","created_at":"2026-07-05T00:04:47.316755+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.06543v1","created_at":"2026-07-05T00:04:47.316755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.06543","created_at":"2026-07-05T00:04:47.316755+00:00"},{"alias_kind":"pith_short_12","alias_value":"X3EMC6F7ZCSM","created_at":"2026-07-05T00:04:47.316755+00:00"},{"alias_kind":"pith_short_16","alias_value":"X3EMC6F7ZCSMRGGQ","created_at":"2026-07-05T00:04:47.316755+00:00"},{"alias_kind":"pith_short_8","alias_value":"X3EMC6F7","created_at":"2026-07-05T00:04:47.316755+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.13276","citing_title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X3EMC6F7ZCSMRGGQ3LQ2DZBXHZ","json":"https://pith.science/pith/X3EMC6F7ZCSMRGGQ3LQ2DZBXHZ.json","graph_json":"https://pith.science/api/pith-number/X3EMC6F7ZCSMRGGQ3LQ2DZBXHZ/graph.json","events_json":"https://pith.science/api/pith-number/X3EMC6F7ZCSMRGGQ3LQ2DZBXHZ/events.json","paper":"https://pith.science/paper/X3EMC6F7"},"agent_actions":{"view_html":"https://pith.science/pith/X3EMC6F7ZCSMRGGQ3LQ2DZBXHZ","download_json":"https://pith.science/pith/X3EMC6F7ZCSMRGGQ3LQ2DZBXHZ.json","view_paper":"https://pith.science/paper/X3EMC6F7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.06543&json=true","fetch_graph":"https://pith.science/api/pith-number/X3EMC6F7ZCSMRGGQ3LQ2DZBXHZ/graph.json","fetch_events":"https://pith.science/api/pith-number/X3EMC6F7ZCSMRGGQ3LQ2DZBXHZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X3EMC6F7ZCSMRGGQ3LQ2DZBXHZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X3EMC6F7ZCSMRGGQ3LQ2DZBXHZ/action/storage_attestation","attest_author":"https://pith.science/pith/X3EMC6F7ZCSMRGGQ3LQ2DZBXHZ/action/author_attestation","sign_citation":"https://pith.science/pith/X3EMC6F7ZCSMRGGQ3LQ2DZBXHZ/action/citation_signature","submit_replication":"https://pith.science/pith/X3EMC6F7ZCSMRGGQ3LQ2DZBXHZ/action/replication_record"}},"created_at":"2026-07-05T00:04:47.316755+00:00","updated_at":"2026-07-05T00:04:47.316755+00:00"}