{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4P2CKHJEUAPTY35N2FYYKURKUA","short_pith_number":"pith:4P2CKHJE","schema_version":"1.0","canonical_sha256":"e3f4251d24a01f3c6fadd17185522aa016b751c654427605f80b4ac24eb3642c","source":{"kind":"arxiv","id":"1909.11793","version":2},"attestation_state":"computed","paper":{"title":"MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bryan Perozzi, John Palowitch","submitted_at":"2019-09-25T22:12:08Z","abstract_excerpt":"Are Graph Neural Networks (GNNs) fair? In many real world graphs, the formation of edges is related to certain node attributes (e.g. gender, community, reputation). In this case, standard GNNs using these edges will be biased by this information, as it is encoded in the structure of the adjacency matrix itself. In this paper, we show that when metadata is correlated with the formation of node neighborhoods, unsupervised node embedding dimensions learn this metadata. This bias implies an inability to control for important covariates in real-world applications, such as recommendation systems. To"},"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":"1909.11793","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T22:12:08Z","cross_cats_sorted":["cs.SI","stat.ML"],"title_canon_sha256":"694fc14c3ef9813a2c7a1c8db6216b0cf009ca0417ad2e76cf18245019dce083","abstract_canon_sha256":"8c168033ec19ba254671d152bf9360121bb874a41e9deafa9a3d45870be7bbed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:20.366787Z","signature_b64":"kztV/YmnXZNVA8oiiH+ns717N5zAg3wIb7l7T+nY/ez+KKHjRl051IBR9ewtg26DYSDzWBH6u0pjT0V4M0MZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3f4251d24a01f3c6fadd17185522aa016b751c654427605f80b4ac24eb3642c","last_reissued_at":"2026-07-05T00:43:20.366340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:20.366340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bryan Perozzi, John Palowitch","submitted_at":"2019-09-25T22:12:08Z","abstract_excerpt":"Are Graph Neural Networks (GNNs) fair? In many real world graphs, the formation of edges is related to certain node attributes (e.g. gender, community, reputation). In this case, standard GNNs using these edges will be biased by this information, as it is encoded in the structure of the adjacency matrix itself. In this paper, we show that when metadata is correlated with the formation of node neighborhoods, unsupervised node embedding dimensions learn this metadata. This bias implies an inability to control for important covariates in real-world applications, such as recommendation systems. To"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11793","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/1909.11793/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":"1909.11793","created_at":"2026-07-05T00:43:20.366397+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.11793v2","created_at":"2026-07-05T00:43:20.366397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11793","created_at":"2026-07-05T00:43:20.366397+00:00"},{"alias_kind":"pith_short_12","alias_value":"4P2CKHJEUAPT","created_at":"2026-07-05T00:43:20.366397+00:00"},{"alias_kind":"pith_short_16","alias_value":"4P2CKHJEUAPTY35N","created_at":"2026-07-05T00:43:20.366397+00:00"},{"alias_kind":"pith_short_8","alias_value":"4P2CKHJE","created_at":"2026-07-05T00:43:20.366397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.05304","citing_title":"Self-Attention Based Multi-Scale Graph Auto-Encoder Network of 3D Meshes","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4P2CKHJEUAPTY35N2FYYKURKUA","json":"https://pith.science/pith/4P2CKHJEUAPTY35N2FYYKURKUA.json","graph_json":"https://pith.science/api/pith-number/4P2CKHJEUAPTY35N2FYYKURKUA/graph.json","events_json":"https://pith.science/api/pith-number/4P2CKHJEUAPTY35N2FYYKURKUA/events.json","paper":"https://pith.science/paper/4P2CKHJE"},"agent_actions":{"view_html":"https://pith.science/pith/4P2CKHJEUAPTY35N2FYYKURKUA","download_json":"https://pith.science/pith/4P2CKHJEUAPTY35N2FYYKURKUA.json","view_paper":"https://pith.science/paper/4P2CKHJE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.11793&json=true","fetch_graph":"https://pith.science/api/pith-number/4P2CKHJEUAPTY35N2FYYKURKUA/graph.json","fetch_events":"https://pith.science/api/pith-number/4P2CKHJEUAPTY35N2FYYKURKUA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4P2CKHJEUAPTY35N2FYYKURKUA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4P2CKHJEUAPTY35N2FYYKURKUA/action/storage_attestation","attest_author":"https://pith.science/pith/4P2CKHJEUAPTY35N2FYYKURKUA/action/author_attestation","sign_citation":"https://pith.science/pith/4P2CKHJEUAPTY35N2FYYKURKUA/action/citation_signature","submit_replication":"https://pith.science/pith/4P2CKHJEUAPTY35N2FYYKURKUA/action/replication_record"}},"created_at":"2026-07-05T00:43:20.366397+00:00","updated_at":"2026-07-05T00:43:20.366397+00:00"}