{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:W53T5COWKVZ56CPMVOUG56W4AA","short_pith_number":"pith:W53T5COW","schema_version":"1.0","canonical_sha256":"b7773e89d65573df09ecaba86efadc000ff3d1d6426c22280f5e1d21b96e0df2","source":{"kind":"arxiv","id":"2201.08549","version":1},"attestation_state":"computed","paper":{"title":"Fair Node Representation Learning via Adaptive Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"O. Deniz Kose, Yanning Shen","submitted_at":"2022-01-21T05:49:15Z","abstract_excerpt":"Node representation learning has demonstrated its efficacy for various applications on graphs, which leads to increasing attention towards the area. However, fairness is a largely under-explored territory within the field, which may lead to biased results towards underrepresented groups in ensuing tasks. To this end, this work theoretically explains the sources of bias in node representations obtained via Graph Neural Networks (GNNs). Our analysis reveals that both nodal features and graph structure lead to bias in the obtained representations. Building upon the analysis, fairness-aware data a"},"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":"2201.08549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-21T05:49:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1d047a7ad03fa62b8a8b913ceea65e4f5555ac7caa97e8e9a5683312e8b2fa06","abstract_canon_sha256":"ded947a1e46abe7c1e9244b5e93789fb299d93eb639f2162254395ca4631b95e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:50:29.595785Z","signature_b64":"9vJSgTfnyiUIOX80anUyH7bypFnWMZTe3XP4a5N6/oGulbZnDSUhjRR51WNSJufO+jfYqRhIg/9YU8TcnPxiBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7773e89d65573df09ecaba86efadc000ff3d1d6426c22280f5e1d21b96e0df2","last_reissued_at":"2026-07-05T03:50:29.595232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:50:29.595232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fair Node Representation Learning via Adaptive Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"O. Deniz Kose, Yanning Shen","submitted_at":"2022-01-21T05:49:15Z","abstract_excerpt":"Node representation learning has demonstrated its efficacy for various applications on graphs, which leads to increasing attention towards the area. However, fairness is a largely under-explored territory within the field, which may lead to biased results towards underrepresented groups in ensuing tasks. To this end, this work theoretically explains the sources of bias in node representations obtained via Graph Neural Networks (GNNs). Our analysis reveals that both nodal features and graph structure lead to bias in the obtained representations. Building upon the analysis, fairness-aware data a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.08549","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/2201.08549/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":"2201.08549","created_at":"2026-07-05T03:50:29.595299+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.08549v1","created_at":"2026-07-05T03:50:29.595299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.08549","created_at":"2026-07-05T03:50:29.595299+00:00"},{"alias_kind":"pith_short_12","alias_value":"W53T5COWKVZ5","created_at":"2026-07-05T03:50:29.595299+00:00"},{"alias_kind":"pith_short_16","alias_value":"W53T5COWKVZ56CPM","created_at":"2026-07-05T03:50:29.595299+00:00"},{"alias_kind":"pith_short_8","alias_value":"W53T5COW","created_at":"2026-07-05T03:50:29.595299+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00595","citing_title":"Unbiased GNN Learning via Fairness-Aware Subgraph Diffusion","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W53T5COWKVZ56CPMVOUG56W4AA","json":"https://pith.science/pith/W53T5COWKVZ56CPMVOUG56W4AA.json","graph_json":"https://pith.science/api/pith-number/W53T5COWKVZ56CPMVOUG56W4AA/graph.json","events_json":"https://pith.science/api/pith-number/W53T5COWKVZ56CPMVOUG56W4AA/events.json","paper":"https://pith.science/paper/W53T5COW"},"agent_actions":{"view_html":"https://pith.science/pith/W53T5COWKVZ56CPMVOUG56W4AA","download_json":"https://pith.science/pith/W53T5COWKVZ56CPMVOUG56W4AA.json","view_paper":"https://pith.science/paper/W53T5COW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.08549&json=true","fetch_graph":"https://pith.science/api/pith-number/W53T5COWKVZ56CPMVOUG56W4AA/graph.json","fetch_events":"https://pith.science/api/pith-number/W53T5COWKVZ56CPMVOUG56W4AA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W53T5COWKVZ56CPMVOUG56W4AA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W53T5COWKVZ56CPMVOUG56W4AA/action/storage_attestation","attest_author":"https://pith.science/pith/W53T5COWKVZ56CPMVOUG56W4AA/action/author_attestation","sign_citation":"https://pith.science/pith/W53T5COWKVZ56CPMVOUG56W4AA/action/citation_signature","submit_replication":"https://pith.science/pith/W53T5COWKVZ56CPMVOUG56W4AA/action/replication_record"}},"created_at":"2026-07-05T03:50:29.595299+00:00","updated_at":"2026-07-05T03:50:29.595299+00:00"}