{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6GIAE7XIQEAELOCJJNV4EIMPQJ","short_pith_number":"pith:6GIAE7XI","schema_version":"1.0","canonical_sha256":"f190027ee8810045b8494b6bc2218f827c51f8f0dd86fb766ca6798a5b5579e3","source":{"kind":"arxiv","id":"2110.13957","version":4},"attestation_state":"computed","paper":{"title":"Unbiased Graph Embedding with Biased Graph Observations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hongning Wang, Jundong Li, Lu Lin, Nan Wang","submitted_at":"2021-10-26T18:44:37Z","abstract_excerpt":"Graph embedding techniques are pivotal in real-world machine learning tasks that operate on graph-structured data, such as social recommendation and protein structure modeling. Embeddings are mostly performed on the node level for learning representations of each node. Since the formation of a graph is inevitably affected by certain sensitive node attributes, the node embeddings can inherit such sensitive information and introduce undesirable biases in downstream tasks. Most existing works impose ad-hoc constraints on the node embeddings to restrict their distributions for unbiasedness/fairnes"},"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":"2110.13957","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-26T18:44:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eabe716da2eb0d0cb584d2deaf1fb8ad7dce70d88458e01407891a8ba13373d0","abstract_canon_sha256":"87986bc71b9c7ae9fd71aa50ad82ec5701af60211c0b29a4fb74cc1a0de70a00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:17.947822Z","signature_b64":"zmVFn42AjHPXd40BvAxOblU8uq/dLkQXckQXTzcRuSeQJGdj1w8kGERtrhfDVVMxVhYMCoWFYuQckgb4ZDg1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f190027ee8810045b8494b6bc2218f827c51f8f0dd86fb766ca6798a5b5579e3","last_reissued_at":"2026-07-05T04:17:17.947343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:17.947343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unbiased Graph Embedding with Biased Graph Observations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hongning Wang, Jundong Li, Lu Lin, Nan Wang","submitted_at":"2021-10-26T18:44:37Z","abstract_excerpt":"Graph embedding techniques are pivotal in real-world machine learning tasks that operate on graph-structured data, such as social recommendation and protein structure modeling. Embeddings are mostly performed on the node level for learning representations of each node. Since the formation of a graph is inevitably affected by certain sensitive node attributes, the node embeddings can inherit such sensitive information and introduce undesirable biases in downstream tasks. Most existing works impose ad-hoc constraints on the node embeddings to restrict their distributions for unbiasedness/fairnes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.13957","kind":"arxiv","version":4},"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/2110.13957/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":"2110.13957","created_at":"2026-07-05T04:17:17.947403+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.13957v4","created_at":"2026-07-05T04:17:17.947403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.13957","created_at":"2026-07-05T04:17:17.947403+00:00"},{"alias_kind":"pith_short_12","alias_value":"6GIAE7XIQEAE","created_at":"2026-07-05T04:17:17.947403+00:00"},{"alias_kind":"pith_short_16","alias_value":"6GIAE7XIQEAELOCJ","created_at":"2026-07-05T04:17:17.947403+00:00"},{"alias_kind":"pith_short_8","alias_value":"6GIAE7XI","created_at":"2026-07-05T04:17:17.947403+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/6GIAE7XIQEAELOCJJNV4EIMPQJ","json":"https://pith.science/pith/6GIAE7XIQEAELOCJJNV4EIMPQJ.json","graph_json":"https://pith.science/api/pith-number/6GIAE7XIQEAELOCJJNV4EIMPQJ/graph.json","events_json":"https://pith.science/api/pith-number/6GIAE7XIQEAELOCJJNV4EIMPQJ/events.json","paper":"https://pith.science/paper/6GIAE7XI"},"agent_actions":{"view_html":"https://pith.science/pith/6GIAE7XIQEAELOCJJNV4EIMPQJ","download_json":"https://pith.science/pith/6GIAE7XIQEAELOCJJNV4EIMPQJ.json","view_paper":"https://pith.science/paper/6GIAE7XI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.13957&json=true","fetch_graph":"https://pith.science/api/pith-number/6GIAE7XIQEAELOCJJNV4EIMPQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6GIAE7XIQEAELOCJJNV4EIMPQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6GIAE7XIQEAELOCJJNV4EIMPQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6GIAE7XIQEAELOCJJNV4EIMPQJ/action/storage_attestation","attest_author":"https://pith.science/pith/6GIAE7XIQEAELOCJJNV4EIMPQJ/action/author_attestation","sign_citation":"https://pith.science/pith/6GIAE7XIQEAELOCJJNV4EIMPQJ/action/citation_signature","submit_replication":"https://pith.science/pith/6GIAE7XIQEAELOCJJNV4EIMPQJ/action/replication_record"}},"created_at":"2026-07-05T04:17:17.947403+00:00","updated_at":"2026-07-05T04:17:17.947403+00:00"}