{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JP42LRJYSQ7G43QNC3H5ASITRW","short_pith_number":"pith:JP42LRJY","schema_version":"1.0","canonical_sha256":"4bf9a5c538943e6e6e0d16cfd049138daa75f704f860f32858489f12b2f2a4e7","source":{"kind":"arxiv","id":"2306.11132","version":1},"attestation_state":"computed","paper":{"title":"Fairness-aware Message Passing for Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guoji Fu, Huaisheng Zhu, Suhang Wang, Teng Xiao, Zhimeng Guo, Zhiwei Zhang","submitted_at":"2023-06-19T19:31:35Z","abstract_excerpt":"Graph Neural Networks (GNNs) have shown great power in various domains. However, their predictions may inherit societal biases on sensitive attributes, limiting their adoption in real-world applications. Although many efforts have been taken for fair GNNs, most existing works just adopt widely used fairness techniques in machine learning to graph domains and ignore or don't have a thorough understanding of the message passing mechanism with fairness constraints, which is a distinctive feature of GNNs. To fill the gap, we propose a novel fairness-aware message passing framework GMMD, which is d"},"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":"2306.11132","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-19T19:31:35Z","cross_cats_sorted":[],"title_canon_sha256":"bc4630f3408bf794230a91e80f56e5a79891647171b79508650921eeb891e728","abstract_canon_sha256":"ca873a20952ddcaba16c4e2f322953f77b71ecaeed3c767613498dbc0e0ee35e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:22:16.417149Z","signature_b64":"EUdTFN01r2NEAFOBJ6gUiS7YvjxYCysBvOS707N7j5Zdzdh1FDsz8uoNQfa0Kx/sezET/RxQVTwhwFozXWz3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bf9a5c538943e6e6e0d16cfd049138daa75f704f860f32858489f12b2f2a4e7","last_reissued_at":"2026-07-05T06:22:16.416758Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:22:16.416758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fairness-aware Message Passing for Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guoji Fu, Huaisheng Zhu, Suhang Wang, Teng Xiao, Zhimeng Guo, Zhiwei Zhang","submitted_at":"2023-06-19T19:31:35Z","abstract_excerpt":"Graph Neural Networks (GNNs) have shown great power in various domains. However, their predictions may inherit societal biases on sensitive attributes, limiting their adoption in real-world applications. Although many efforts have been taken for fair GNNs, most existing works just adopt widely used fairness techniques in machine learning to graph domains and ignore or don't have a thorough understanding of the message passing mechanism with fairness constraints, which is a distinctive feature of GNNs. To fill the gap, we propose a novel fairness-aware message passing framework GMMD, which is d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11132","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/2306.11132/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":"2306.11132","created_at":"2026-07-05T06:22:16.416816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.11132v1","created_at":"2026-07-05T06:22:16.416816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11132","created_at":"2026-07-05T06:22:16.416816+00:00"},{"alias_kind":"pith_short_12","alias_value":"JP42LRJYSQ7G","created_at":"2026-07-05T06:22:16.416816+00:00"},{"alias_kind":"pith_short_16","alias_value":"JP42LRJYSQ7G43QN","created_at":"2026-07-05T06:22:16.416816+00:00"},{"alias_kind":"pith_short_8","alias_value":"JP42LRJY","created_at":"2026-07-05T06:22:16.416816+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JP42LRJYSQ7G43QNC3H5ASITRW","json":"https://pith.science/pith/JP42LRJYSQ7G43QNC3H5ASITRW.json","graph_json":"https://pith.science/api/pith-number/JP42LRJYSQ7G43QNC3H5ASITRW/graph.json","events_json":"https://pith.science/api/pith-number/JP42LRJYSQ7G43QNC3H5ASITRW/events.json","paper":"https://pith.science/paper/JP42LRJY"},"agent_actions":{"view_html":"https://pith.science/pith/JP42LRJYSQ7G43QNC3H5ASITRW","download_json":"https://pith.science/pith/JP42LRJYSQ7G43QNC3H5ASITRW.json","view_paper":"https://pith.science/paper/JP42LRJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.11132&json=true","fetch_graph":"https://pith.science/api/pith-number/JP42LRJYSQ7G43QNC3H5ASITRW/graph.json","fetch_events":"https://pith.science/api/pith-number/JP42LRJYSQ7G43QNC3H5ASITRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JP42LRJYSQ7G43QNC3H5ASITRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JP42LRJYSQ7G43QNC3H5ASITRW/action/storage_attestation","attest_author":"https://pith.science/pith/JP42LRJYSQ7G43QNC3H5ASITRW/action/author_attestation","sign_citation":"https://pith.science/pith/JP42LRJYSQ7G43QNC3H5ASITRW/action/citation_signature","submit_replication":"https://pith.science/pith/JP42LRJYSQ7G43QNC3H5ASITRW/action/replication_record"}},"created_at":"2026-07-05T06:22:16.416816+00:00","updated_at":"2026-07-05T06:22:16.416816+00:00"}