{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3P75XBL3TSZLVSKJYKIN76T3KN","short_pith_number":"pith:3P75XBL3","schema_version":"1.0","canonical_sha256":"dbffdb857b9cb2bac949c290dffa7b535d6a1d184ead8d619804e5972ec24060","source":{"kind":"arxiv","id":"2106.07451","version":2},"attestation_state":"computed","paper":{"title":"Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Han, Junzhou Huang, Tian Bian, Tingyang Xu, Tongliang Liu, Wenbing Huang, Xuefeng Du, Yixuan Li, Yu Rong","submitted_at":"2021-06-14T14:23:08Z","abstract_excerpt":"Teaching Graph Neural Networks (GNNs) to accurately classify nodes under severely noisy labels is an important problem in real-world graph learning applications, but is currently underexplored. Although pairwise training methods have demonstrated promise in supervised metric learning and unsupervised contrastive learning, they remain less studied on noisy graphs, where the structural pairwise interactions (PI) between nodes are abundant and thus might benefit label noise learning rather than the pointwise methods. This paper bridges the gap by proposing a pairwise framework for noisy node clas"},"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":"2106.07451","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-14T14:23:08Z","cross_cats_sorted":[],"title_canon_sha256":"62f1951fc31fa65f2c0cd4742f87d2ee960594561f56798b47a440039dabac0f","abstract_canon_sha256":"cb70b8de4d076fcdbbc82f5d2ba320822b116fd1cd4311c736efe27652b2de97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:58.550372Z","signature_b64":"gvwa5i8lG1PLRM2Fy0zjbzz+6+TztX8n/XaNuK1zDCLuKCnAl+SPA6cnCOZOUvmvc6D/RghQhQ2abX3RWOE+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbffdb857b9cb2bac949c290dffa7b535d6a1d184ead8d619804e5972ec24060","last_reissued_at":"2026-07-05T06:16:58.549883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:58.549883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Han, Junzhou Huang, Tian Bian, Tingyang Xu, Tongliang Liu, Wenbing Huang, Xuefeng Du, Yixuan Li, Yu Rong","submitted_at":"2021-06-14T14:23:08Z","abstract_excerpt":"Teaching Graph Neural Networks (GNNs) to accurately classify nodes under severely noisy labels is an important problem in real-world graph learning applications, but is currently underexplored. Although pairwise training methods have demonstrated promise in supervised metric learning and unsupervised contrastive learning, they remain less studied on noisy graphs, where the structural pairwise interactions (PI) between nodes are abundant and thus might benefit label noise learning rather than the pointwise methods. This paper bridges the gap by proposing a pairwise framework for noisy node clas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07451","kind":"arxiv","version":2},"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/2106.07451/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":"2106.07451","created_at":"2026-07-05T06:16:58.549942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.07451v2","created_at":"2026-07-05T06:16:58.549942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07451","created_at":"2026-07-05T06:16:58.549942+00:00"},{"alias_kind":"pith_short_12","alias_value":"3P75XBL3TSZL","created_at":"2026-07-05T06:16:58.549942+00:00"},{"alias_kind":"pith_short_16","alias_value":"3P75XBL3TSZLVSKJ","created_at":"2026-07-05T06:16:58.549942+00:00"},{"alias_kind":"pith_short_8","alias_value":"3P75XBL3","created_at":"2026-07-05T06:16:58.549942+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.08952","citing_title":"When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approach","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3P75XBL3TSZLVSKJYKIN76T3KN","json":"https://pith.science/pith/3P75XBL3TSZLVSKJYKIN76T3KN.json","graph_json":"https://pith.science/api/pith-number/3P75XBL3TSZLVSKJYKIN76T3KN/graph.json","events_json":"https://pith.science/api/pith-number/3P75XBL3TSZLVSKJYKIN76T3KN/events.json","paper":"https://pith.science/paper/3P75XBL3"},"agent_actions":{"view_html":"https://pith.science/pith/3P75XBL3TSZLVSKJYKIN76T3KN","download_json":"https://pith.science/pith/3P75XBL3TSZLVSKJYKIN76T3KN.json","view_paper":"https://pith.science/paper/3P75XBL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.07451&json=true","fetch_graph":"https://pith.science/api/pith-number/3P75XBL3TSZLVSKJYKIN76T3KN/graph.json","fetch_events":"https://pith.science/api/pith-number/3P75XBL3TSZLVSKJYKIN76T3KN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3P75XBL3TSZLVSKJYKIN76T3KN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3P75XBL3TSZLVSKJYKIN76T3KN/action/storage_attestation","attest_author":"https://pith.science/pith/3P75XBL3TSZLVSKJYKIN76T3KN/action/author_attestation","sign_citation":"https://pith.science/pith/3P75XBL3TSZLVSKJYKIN76T3KN/action/citation_signature","submit_replication":"https://pith.science/pith/3P75XBL3TSZLVSKJYKIN76T3KN/action/replication_record"}},"created_at":"2026-07-05T06:16:58.549942+00:00","updated_at":"2026-07-05T06:16:58.549942+00:00"}