{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IRABOGZZQDVEQQ6E3ATKX33WSS","short_pith_number":"pith:IRABOGZZ","schema_version":"1.0","canonical_sha256":"4440171b3980ea4843c4d826abef76949432ac5fa647e7a8f9c96858d0511239","source":{"kind":"arxiv","id":"2102.13186","version":3},"attestation_state":"computed","paper":{"title":"Towards a Unified Framework for Fair and Stable Graph Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chirag Agarwal, Himabindu Lakkaraju, Marinka Zitnik","submitted_at":"2021-02-25T21:34:39Z","abstract_excerpt":"As the representations output by Graph Neural Networks (GNNs) are increasingly employed in real-world applications, it becomes important to ensure that these representations are fair and stable. In this work, we establish a key connection between counterfactual fairness and stability and leverage it to propose a novel framework, NIFTY (uNIfying Fairness and stabiliTY), which can be used with any GNN to learn fair and stable representations. We introduce a novel objective function that simultaneously accounts for fairness and stability and develop a layer-wise weight normalization using the Lip"},"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":"2102.13186","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-25T21:34:39Z","cross_cats_sorted":[],"title_canon_sha256":"a2e53c82798f1a85570c1f05a47530e99dc6e3d0f735a14c6a8a37325b53939b","abstract_canon_sha256":"b431887542936a210bdbc4e929673cef75ce2012b24c8324903680dd61f93d82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:37:01.401249Z","signature_b64":"StIItLowmps7wpHfplRLezfyIojkfwrNB4llb7Ll6feXCmRDYWuBwrer5YTWCznf5WImLb+81rmq6lIhbEdUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4440171b3980ea4843c4d826abef76949432ac5fa647e7a8f9c96858d0511239","last_reissued_at":"2026-07-05T04:37:01.400880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:37:01.400880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards a Unified Framework for Fair and Stable Graph Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chirag Agarwal, Himabindu Lakkaraju, Marinka Zitnik","submitted_at":"2021-02-25T21:34:39Z","abstract_excerpt":"As the representations output by Graph Neural Networks (GNNs) are increasingly employed in real-world applications, it becomes important to ensure that these representations are fair and stable. In this work, we establish a key connection between counterfactual fairness and stability and leverage it to propose a novel framework, NIFTY (uNIfying Fairness and stabiliTY), which can be used with any GNN to learn fair and stable representations. We introduce a novel objective function that simultaneously accounts for fairness and stability and develop a layer-wise weight normalization using the Lip"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.13186","kind":"arxiv","version":3},"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/2102.13186/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":"2102.13186","created_at":"2026-07-05T04:37:01.400927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.13186v3","created_at":"2026-07-05T04:37:01.400927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.13186","created_at":"2026-07-05T04:37:01.400927+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRABOGZZQDVE","created_at":"2026-07-05T04:37:01.400927+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRABOGZZQDVEQQ6E","created_at":"2026-07-05T04:37:01.400927+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRABOGZZ","created_at":"2026-07-05T04:37:01.400927+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05101","citing_title":"Counterfactual Methods for Detecting Unfairness in Anti-Money Laundering Algorithms","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IRABOGZZQDVEQQ6E3ATKX33WSS","json":"https://pith.science/pith/IRABOGZZQDVEQQ6E3ATKX33WSS.json","graph_json":"https://pith.science/api/pith-number/IRABOGZZQDVEQQ6E3ATKX33WSS/graph.json","events_json":"https://pith.science/api/pith-number/IRABOGZZQDVEQQ6E3ATKX33WSS/events.json","paper":"https://pith.science/paper/IRABOGZZ"},"agent_actions":{"view_html":"https://pith.science/pith/IRABOGZZQDVEQQ6E3ATKX33WSS","download_json":"https://pith.science/pith/IRABOGZZQDVEQQ6E3ATKX33WSS.json","view_paper":"https://pith.science/paper/IRABOGZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.13186&json=true","fetch_graph":"https://pith.science/api/pith-number/IRABOGZZQDVEQQ6E3ATKX33WSS/graph.json","fetch_events":"https://pith.science/api/pith-number/IRABOGZZQDVEQQ6E3ATKX33WSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRABOGZZQDVEQQ6E3ATKX33WSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRABOGZZQDVEQQ6E3ATKX33WSS/action/storage_attestation","attest_author":"https://pith.science/pith/IRABOGZZQDVEQQ6E3ATKX33WSS/action/author_attestation","sign_citation":"https://pith.science/pith/IRABOGZZQDVEQQ6E3ATKX33WSS/action/citation_signature","submit_replication":"https://pith.science/pith/IRABOGZZQDVEQQ6E3ATKX33WSS/action/replication_record"}},"created_at":"2026-07-05T04:37:01.400927+00:00","updated_at":"2026-07-05T04:37:01.400927+00:00"}