{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EXZVJNCR3WXTT3VNP2BOQTBSGD","short_pith_number":"pith:EXZVJNCR","schema_version":"1.0","canonical_sha256":"25f354b451ddaf39eead7e82e84c3230edccbf08862bb967ac30dc3b8a0fb362","source":{"kind":"arxiv","id":"2405.20790","version":3},"attestation_state":"computed","paper":{"title":"Intersectional Unfairness Discovery","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.LG","authors_text":"Boyu Wang, Changjian Shui, Charles Ling, Gezheng Xu, Qi Chen","submitted_at":"2024-05-31T13:45:52Z","abstract_excerpt":"AI systems have been shown to produce unfair results for certain subgroups of population, highlighting the need to understand bias on certain sensitive attributes. Current research often falls short, primarily focusing on the subgroups characterized by a single sensitive attribute, while neglecting the nature of intersectional fairness of multiple sensitive attributes. This paper focuses on its one fundamental aspect by discovering diverse high-bias subgroups under intersectional sensitive attributes. Specifically, we propose a Bias-Guided Generative Network (BGGN). By treating each bias value"},"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":"2405.20790","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T13:45:52Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"05b7ea17673d1d2d44df15992b8572cbf2e06f70d530d857abbcc7ff48ea0a62","abstract_canon_sha256":"4d701facf22e954e252f9b6be09ad22b9f50ddbd4d960757d9afb99f3674c800"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:41.705485Z","signature_b64":"hs1DIwCC+e/BaTTxOxG0tpUGvf2+B4jmbK7epZe9zreta8xbZdPIB91IgEruKZihtECXlG83injMa2svONtJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25f354b451ddaf39eead7e82e84c3230edccbf08862bb967ac30dc3b8a0fb362","last_reissued_at":"2026-07-05T08:28:41.705052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:41.705052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intersectional Unfairness Discovery","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.LG","authors_text":"Boyu Wang, Changjian Shui, Charles Ling, Gezheng Xu, Qi Chen","submitted_at":"2024-05-31T13:45:52Z","abstract_excerpt":"AI systems have been shown to produce unfair results for certain subgroups of population, highlighting the need to understand bias on certain sensitive attributes. Current research often falls short, primarily focusing on the subgroups characterized by a single sensitive attribute, while neglecting the nature of intersectional fairness of multiple sensitive attributes. This paper focuses on its one fundamental aspect by discovering diverse high-bias subgroups under intersectional sensitive attributes. Specifically, we propose a Bias-Guided Generative Network (BGGN). By treating each bias value"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20790","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/2405.20790/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":"2405.20790","created_at":"2026-07-05T08:28:41.705110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20790v3","created_at":"2026-07-05T08:28:41.705110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20790","created_at":"2026-07-05T08:28:41.705110+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXZVJNCR3WXT","created_at":"2026-07-05T08:28:41.705110+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXZVJNCR3WXTT3VN","created_at":"2026-07-05T08:28:41.705110+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXZVJNCR","created_at":"2026-07-05T08:28:41.705110+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00849","citing_title":"Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EXZVJNCR3WXTT3VNP2BOQTBSGD","json":"https://pith.science/pith/EXZVJNCR3WXTT3VNP2BOQTBSGD.json","graph_json":"https://pith.science/api/pith-number/EXZVJNCR3WXTT3VNP2BOQTBSGD/graph.json","events_json":"https://pith.science/api/pith-number/EXZVJNCR3WXTT3VNP2BOQTBSGD/events.json","paper":"https://pith.science/paper/EXZVJNCR"},"agent_actions":{"view_html":"https://pith.science/pith/EXZVJNCR3WXTT3VNP2BOQTBSGD","download_json":"https://pith.science/pith/EXZVJNCR3WXTT3VNP2BOQTBSGD.json","view_paper":"https://pith.science/paper/EXZVJNCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20790&json=true","fetch_graph":"https://pith.science/api/pith-number/EXZVJNCR3WXTT3VNP2BOQTBSGD/graph.json","fetch_events":"https://pith.science/api/pith-number/EXZVJNCR3WXTT3VNP2BOQTBSGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXZVJNCR3WXTT3VNP2BOQTBSGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXZVJNCR3WXTT3VNP2BOQTBSGD/action/storage_attestation","attest_author":"https://pith.science/pith/EXZVJNCR3WXTT3VNP2BOQTBSGD/action/author_attestation","sign_citation":"https://pith.science/pith/EXZVJNCR3WXTT3VNP2BOQTBSGD/action/citation_signature","submit_replication":"https://pith.science/pith/EXZVJNCR3WXTT3VNP2BOQTBSGD/action/replication_record"}},"created_at":"2026-07-05T08:28:41.705110+00:00","updated_at":"2026-07-05T08:28:41.705110+00:00"}