{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:R2ZU4P4XZZXWIZUUGX2C5XNHGV","short_pith_number":"pith:R2ZU4P4X","schema_version":"1.0","canonical_sha256":"8eb34e3f97ce6f64669435f42edda73570250318162dfcc327c12f55376ad916","source":{"kind":"arxiv","id":"1807.08362","version":3},"attestation_state":"computed","paper":{"title":"An Intersectional Definition of Fairness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","stat.ML"],"primary_cat":"cs.LG","authors_text":"James Foulds, Kamrun Naher Keya, Rashidul Islam, Shimei Pan","submitted_at":"2018-07-22T20:37:45Z","abstract_excerpt":"We propose definitions of fairness in machine learning and artificial intelligence systems that are informed by the framework of intersectionality, a critical lens arising from the Humanities literature which analyzes how interlocking systems of power and oppression affect individuals along overlapping dimensions including gender, race, sexual orientation, class, and disability. We show that our criteria behave sensibly for any subset of the set of protected attributes, and we prove economic, privacy, and generalization guarantees. We provide a learning algorithm which respects our intersectio"},"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":"1807.08362","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-22T20:37:45Z","cross_cats_sorted":["cs.CY","stat.ML"],"title_canon_sha256":"8323f9f993b7bbf728153d245ede8ad3d1353aa4cfd8897ba60361846f5f31d2","abstract_canon_sha256":"4864bd5a96f6fbfea1fb9e2329feb546ce9ef7f7582ae7b96c491fa23b6c193f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:03:12.237146Z","signature_b64":"Mw3AyYrFDJD42Y0XQSHlUf2EWwmGtBl0tMf6HRz+jkSfYkn9i6wJwS/BhoYDJRlTgD6mtA0Z/BGWtnMd2u4oDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8eb34e3f97ce6f64669435f42edda73570250318162dfcc327c12f55376ad916","last_reissued_at":"2026-07-05T00:03:12.236703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:03:12.236703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Intersectional Definition of Fairness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","stat.ML"],"primary_cat":"cs.LG","authors_text":"James Foulds, Kamrun Naher Keya, Rashidul Islam, Shimei Pan","submitted_at":"2018-07-22T20:37:45Z","abstract_excerpt":"We propose definitions of fairness in machine learning and artificial intelligence systems that are informed by the framework of intersectionality, a critical lens arising from the Humanities literature which analyzes how interlocking systems of power and oppression affect individuals along overlapping dimensions including gender, race, sexual orientation, class, and disability. We show that our criteria behave sensibly for any subset of the set of protected attributes, and we prove economic, privacy, and generalization guarantees. We provide a learning algorithm which respects our intersectio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.08362","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/1807.08362/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":"1807.08362","created_at":"2026-07-05T00:03:12.236760+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.08362v3","created_at":"2026-07-05T00:03:12.236760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.08362","created_at":"2026-07-05T00:03:12.236760+00:00"},{"alias_kind":"pith_short_12","alias_value":"R2ZU4P4XZZXW","created_at":"2026-07-05T00:03:12.236760+00:00"},{"alias_kind":"pith_short_16","alias_value":"R2ZU4P4XZZXWIZUU","created_at":"2026-07-05T00:03:12.236760+00:00"},{"alias_kind":"pith_short_8","alias_value":"R2ZU4P4X","created_at":"2026-07-05T00:03:12.236760+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04858","citing_title":"FairLogue: A Toolkit for Intersectional Fairness Analysis in Clinical Machine Learning Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16450","citing_title":"Evaluating Intersectional Fairness across Clinical Machine Learning Use Cases using Fairlogue and the All of Us Research Program","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R2ZU4P4XZZXWIZUUGX2C5XNHGV","json":"https://pith.science/pith/R2ZU4P4XZZXWIZUUGX2C5XNHGV.json","graph_json":"https://pith.science/api/pith-number/R2ZU4P4XZZXWIZUUGX2C5XNHGV/graph.json","events_json":"https://pith.science/api/pith-number/R2ZU4P4XZZXWIZUUGX2C5XNHGV/events.json","paper":"https://pith.science/paper/R2ZU4P4X"},"agent_actions":{"view_html":"https://pith.science/pith/R2ZU4P4XZZXWIZUUGX2C5XNHGV","download_json":"https://pith.science/pith/R2ZU4P4XZZXWIZUUGX2C5XNHGV.json","view_paper":"https://pith.science/paper/R2ZU4P4X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.08362&json=true","fetch_graph":"https://pith.science/api/pith-number/R2ZU4P4XZZXWIZUUGX2C5XNHGV/graph.json","fetch_events":"https://pith.science/api/pith-number/R2ZU4P4XZZXWIZUUGX2C5XNHGV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R2ZU4P4XZZXWIZUUGX2C5XNHGV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R2ZU4P4XZZXWIZUUGX2C5XNHGV/action/storage_attestation","attest_author":"https://pith.science/pith/R2ZU4P4XZZXWIZUUGX2C5XNHGV/action/author_attestation","sign_citation":"https://pith.science/pith/R2ZU4P4XZZXWIZUUGX2C5XNHGV/action/citation_signature","submit_replication":"https://pith.science/pith/R2ZU4P4XZZXWIZUUGX2C5XNHGV/action/replication_record"}},"created_at":"2026-07-05T00:03:12.236760+00:00","updated_at":"2026-07-05T00:03:12.236760+00:00"}