{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3LA5VQRJYLJOW3ABJGDTYRI6V6","short_pith_number":"pith:3LA5VQRJ","schema_version":"1.0","canonical_sha256":"dac1dac229c2d2eb6c0149873c451eafae15f0bf80a82cf535ad82720a43bdf1","source":{"kind":"arxiv","id":"2210.01002","version":1},"attestation_state":"computed","paper":{"title":"ASGNN: Graph Neural Networks with Adaptive Structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Songtao Lu, Zengfeng Huang, Zepeng Zhang, Ziping Zhao","submitted_at":"2022-10-03T15:10:40Z","abstract_excerpt":"The graph neural network (GNN) models have presented impressive achievements in numerous machine learning tasks. However, many existing GNN models are shown to be vulnerable to adversarial attacks, which creates a stringent need to build robust GNN architectures. In this work, we propose a novel interpretable message passing scheme with adaptive structure (ASMP) to defend against adversarial attacks on graph structure. Layers in ASMP are derived based on optimization steps that minimize an objective function that learns the node feature and the graph structure simultaneously. ASMP is adaptive "},"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":"2210.01002","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T15:10:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"82c7c806727a8bd9d46ae694e09cb4a09703e688a8c2d25b3096ba253a4568c5","abstract_canon_sha256":"928f344bd5fbfb260f72cb8cc7dd6e5bb7e31917c1151551fab9a8dbdad39ac0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:50.089812Z","signature_b64":"/PC2g6Px6veTgD8D4o6eZrj8/6OtWXPcJUVsLCVmjTUxATRAoNSyeg0UEtNKP/vIKWWiSL3gZpPlmMKvEbJWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dac1dac229c2d2eb6c0149873c451eafae15f0bf80a82cf535ad82720a43bdf1","last_reissued_at":"2026-07-05T05:02:50.089398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:50.089398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ASGNN: Graph Neural Networks with Adaptive Structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Songtao Lu, Zengfeng Huang, Zepeng Zhang, Ziping Zhao","submitted_at":"2022-10-03T15:10:40Z","abstract_excerpt":"The graph neural network (GNN) models have presented impressive achievements in numerous machine learning tasks. However, many existing GNN models are shown to be vulnerable to adversarial attacks, which creates a stringent need to build robust GNN architectures. In this work, we propose a novel interpretable message passing scheme with adaptive structure (ASMP) to defend against adversarial attacks on graph structure. Layers in ASMP are derived based on optimization steps that minimize an objective function that learns the node feature and the graph structure simultaneously. ASMP is adaptive "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01002","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/2210.01002/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":"2210.01002","created_at":"2026-07-05T05:02:50.089455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.01002v1","created_at":"2026-07-05T05:02:50.089455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01002","created_at":"2026-07-05T05:02:50.089455+00:00"},{"alias_kind":"pith_short_12","alias_value":"3LA5VQRJYLJO","created_at":"2026-07-05T05:02:50.089455+00:00"},{"alias_kind":"pith_short_16","alias_value":"3LA5VQRJYLJOW3AB","created_at":"2026-07-05T05:02:50.089455+00:00"},{"alias_kind":"pith_short_8","alias_value":"3LA5VQRJ","created_at":"2026-07-05T05:02:50.089455+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.13137","citing_title":"Domain Adaptive Unfolded Graph Neural Networks","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3LA5VQRJYLJOW3ABJGDTYRI6V6","json":"https://pith.science/pith/3LA5VQRJYLJOW3ABJGDTYRI6V6.json","graph_json":"https://pith.science/api/pith-number/3LA5VQRJYLJOW3ABJGDTYRI6V6/graph.json","events_json":"https://pith.science/api/pith-number/3LA5VQRJYLJOW3ABJGDTYRI6V6/events.json","paper":"https://pith.science/paper/3LA5VQRJ"},"agent_actions":{"view_html":"https://pith.science/pith/3LA5VQRJYLJOW3ABJGDTYRI6V6","download_json":"https://pith.science/pith/3LA5VQRJYLJOW3ABJGDTYRI6V6.json","view_paper":"https://pith.science/paper/3LA5VQRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.01002&json=true","fetch_graph":"https://pith.science/api/pith-number/3LA5VQRJYLJOW3ABJGDTYRI6V6/graph.json","fetch_events":"https://pith.science/api/pith-number/3LA5VQRJYLJOW3ABJGDTYRI6V6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3LA5VQRJYLJOW3ABJGDTYRI6V6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3LA5VQRJYLJOW3ABJGDTYRI6V6/action/storage_attestation","attest_author":"https://pith.science/pith/3LA5VQRJYLJOW3ABJGDTYRI6V6/action/author_attestation","sign_citation":"https://pith.science/pith/3LA5VQRJYLJOW3ABJGDTYRI6V6/action/citation_signature","submit_replication":"https://pith.science/pith/3LA5VQRJYLJOW3ABJGDTYRI6V6/action/replication_record"}},"created_at":"2026-07-05T05:02:50.089455+00:00","updated_at":"2026-07-05T05:02:50.089455+00:00"}