{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XTVDSWE27UYKGX4VBDONKMXANY","short_pith_number":"pith:XTVDSWE2","schema_version":"1.0","canonical_sha256":"bcea39589afd30a35f9508dcd532e06e34901539e2f9e97da8a16e5e8cb0baf5","source":{"kind":"arxiv","id":"2110.14855","version":1},"attestation_state":"computed","paper":{"title":"CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haotian Xue, Kai Guo, Kaixiong Zhou, Tianlong Chen, Xia Hu, Xin Wang, Yi Chang","submitted_at":"2021-10-28T02:28:13Z","abstract_excerpt":"Despite the recent advances of graph neural networks (GNNs) in modeling graph data, the training of GNNs on large datasets is notoriously hard due to the overfitting. Adversarial training, which augments data with the worst-case adversarial examples, has been widely demonstrated to improve model's robustness against adversarial attacks and generalization ability. However, while the previous adversarial training generally focuses on protecting GNNs from spiteful attacks, it remains unclear how the adversarial training could improve the generalization abilities of GNNs in the graph analytics pro"},"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":"2110.14855","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-28T02:28:13Z","cross_cats_sorted":[],"title_canon_sha256":"84d02a3f07af8fb6682c01067ceeb3e4fcd00b479c7fa0a3dabe05219e529350","abstract_canon_sha256":"3c7f0b80c7032ba1588abcc367d00e7e609f9ad788064dd17c14ab63df8ad53e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:48.378826Z","signature_b64":"wyxjxgl/svAuYY0+yGn9LOQCm1yWh33oeMKXU4JpI4inq+pAygWC1JeyYykI7okLPsxyyWN9sUFnQqGtYbVGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcea39589afd30a35f9508dcd532e06e34901539e2f9e97da8a16e5e8cb0baf5","last_reissued_at":"2026-07-05T03:26:48.377289Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:48.377289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haotian Xue, Kai Guo, Kaixiong Zhou, Tianlong Chen, Xia Hu, Xin Wang, Yi Chang","submitted_at":"2021-10-28T02:28:13Z","abstract_excerpt":"Despite the recent advances of graph neural networks (GNNs) in modeling graph data, the training of GNNs on large datasets is notoriously hard due to the overfitting. Adversarial training, which augments data with the worst-case adversarial examples, has been widely demonstrated to improve model's robustness against adversarial attacks and generalization ability. However, while the previous adversarial training generally focuses on protecting GNNs from spiteful attacks, it remains unclear how the adversarial training could improve the generalization abilities of GNNs in the graph analytics pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14855","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/2110.14855/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":"2110.14855","created_at":"2026-07-05T03:26:48.378328+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.14855v1","created_at":"2026-07-05T03:26:48.378328+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14855","created_at":"2026-07-05T03:26:48.378328+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTVDSWE27UYK","created_at":"2026-07-05T03:26:48.378328+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTVDSWE27UYKGX4V","created_at":"2026-07-05T03:26:48.378328+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTVDSWE2","created_at":"2026-07-05T03:26:48.378328+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00387","citing_title":"Unifying Adversarial Perturbation for Graph Neural Networks","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XTVDSWE27UYKGX4VBDONKMXANY","json":"https://pith.science/pith/XTVDSWE27UYKGX4VBDONKMXANY.json","graph_json":"https://pith.science/api/pith-number/XTVDSWE27UYKGX4VBDONKMXANY/graph.json","events_json":"https://pith.science/api/pith-number/XTVDSWE27UYKGX4VBDONKMXANY/events.json","paper":"https://pith.science/paper/XTVDSWE2"},"agent_actions":{"view_html":"https://pith.science/pith/XTVDSWE27UYKGX4VBDONKMXANY","download_json":"https://pith.science/pith/XTVDSWE27UYKGX4VBDONKMXANY.json","view_paper":"https://pith.science/paper/XTVDSWE2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.14855&json=true","fetch_graph":"https://pith.science/api/pith-number/XTVDSWE27UYKGX4VBDONKMXANY/graph.json","fetch_events":"https://pith.science/api/pith-number/XTVDSWE27UYKGX4VBDONKMXANY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTVDSWE27UYKGX4VBDONKMXANY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTVDSWE27UYKGX4VBDONKMXANY/action/storage_attestation","attest_author":"https://pith.science/pith/XTVDSWE27UYKGX4VBDONKMXANY/action/author_attestation","sign_citation":"https://pith.science/pith/XTVDSWE27UYKGX4VBDONKMXANY/action/citation_signature","submit_replication":"https://pith.science/pith/XTVDSWE27UYKGX4VBDONKMXANY/action/replication_record"}},"created_at":"2026-07-05T03:26:48.378328+00:00","updated_at":"2026-07-05T03:26:48.378328+00:00"}