{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6XPBVLC4TOQ3FC4M3XEIP2ZNUN","short_pith_number":"pith:6XPBVLC4","schema_version":"1.0","canonical_sha256":"f5de1aac5c9ba1b28b8cddc887eb2da362b136fc4b138dc5ffd5de253bc5aa08","source":{"kind":"arxiv","id":"2208.01853","version":1},"attestation_state":"computed","paper":{"title":"Robust Graph Neural Networks using Weighted Graph Laplacian","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bharat Runwal, Sandeep Kumar, Vivek","submitted_at":"2022-08-03T05:36:35Z","abstract_excerpt":"Graph neural network (GNN) is achieving remarkable performances in a variety of application domains. However, GNN is vulnerable to noise and adversarial attacks in input data. Making GNN robust against noises and adversarial attacks is an important problem. The existing defense methods for GNNs are computationally demanding and are not scalable. In this paper, we propose a generic framework for robustifying GNN known as Weighted Laplacian GNN (RWL-GNN). The method combines Weighted Graph Laplacian learning with the GNN implementation. The proposed method benefits from the positive semi-definit"},"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":"2208.01853","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-03T05:36:35Z","cross_cats_sorted":[],"title_canon_sha256":"039f27a6650b7e5399d291ada0ee6138577d5b310e964a87bffbbb9a114fd849","abstract_canon_sha256":"9db349f8a2328aab238faa335026c8e20c94826af3e9fe96a66ac53aca6d1ff2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:45:50.320109Z","signature_b64":"E4U+BYCdrZKc+rxkxjkTO+zkIKgqsYtsweMp4ehMJHTZjEwyKZ9Q1O5iH840wnaizHGl6v2JYgTNnLNL71BiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5de1aac5c9ba1b28b8cddc887eb2da362b136fc4b138dc5ffd5de253bc5aa08","last_reissued_at":"2026-07-05T04:45:50.319641Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:45:50.319641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Graph Neural Networks using Weighted Graph Laplacian","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bharat Runwal, Sandeep Kumar, Vivek","submitted_at":"2022-08-03T05:36:35Z","abstract_excerpt":"Graph neural network (GNN) is achieving remarkable performances in a variety of application domains. However, GNN is vulnerable to noise and adversarial attacks in input data. Making GNN robust against noises and adversarial attacks is an important problem. The existing defense methods for GNNs are computationally demanding and are not scalable. In this paper, we propose a generic framework for robustifying GNN known as Weighted Laplacian GNN (RWL-GNN). The method combines Weighted Graph Laplacian learning with the GNN implementation. The proposed method benefits from the positive semi-definit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.01853","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/2208.01853/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":"2208.01853","created_at":"2026-07-05T04:45:50.319698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.01853v1","created_at":"2026-07-05T04:45:50.319698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.01853","created_at":"2026-07-05T04:45:50.319698+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XPBVLC4TOQ3","created_at":"2026-07-05T04:45:50.319698+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XPBVLC4TOQ3FC4M","created_at":"2026-07-05T04:45:50.319698+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XPBVLC4","created_at":"2026-07-05T04:45:50.319698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23517","citing_title":"Collapsed Effective Operators for Higher-order Structures","ref_index":79,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6XPBVLC4TOQ3FC4M3XEIP2ZNUN","json":"https://pith.science/pith/6XPBVLC4TOQ3FC4M3XEIP2ZNUN.json","graph_json":"https://pith.science/api/pith-number/6XPBVLC4TOQ3FC4M3XEIP2ZNUN/graph.json","events_json":"https://pith.science/api/pith-number/6XPBVLC4TOQ3FC4M3XEIP2ZNUN/events.json","paper":"https://pith.science/paper/6XPBVLC4"},"agent_actions":{"view_html":"https://pith.science/pith/6XPBVLC4TOQ3FC4M3XEIP2ZNUN","download_json":"https://pith.science/pith/6XPBVLC4TOQ3FC4M3XEIP2ZNUN.json","view_paper":"https://pith.science/paper/6XPBVLC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.01853&json=true","fetch_graph":"https://pith.science/api/pith-number/6XPBVLC4TOQ3FC4M3XEIP2ZNUN/graph.json","fetch_events":"https://pith.science/api/pith-number/6XPBVLC4TOQ3FC4M3XEIP2ZNUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XPBVLC4TOQ3FC4M3XEIP2ZNUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XPBVLC4TOQ3FC4M3XEIP2ZNUN/action/storage_attestation","attest_author":"https://pith.science/pith/6XPBVLC4TOQ3FC4M3XEIP2ZNUN/action/author_attestation","sign_citation":"https://pith.science/pith/6XPBVLC4TOQ3FC4M3XEIP2ZNUN/action/citation_signature","submit_replication":"https://pith.science/pith/6XPBVLC4TOQ3FC4M3XEIP2ZNUN/action/replication_record"}},"created_at":"2026-07-05T04:45:50.319698+00:00","updated_at":"2026-07-05T04:45:50.319698+00:00"}