{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TILCNRL2NY2DU7TXF5NBZXOF6P","short_pith_number":"pith:TILCNRL2","schema_version":"1.0","canonical_sha256":"9a1626c57a6e343a7e772f5a1cddc5f3d58df5166530f4f9a6365499f16cbb4f","source":{"kind":"arxiv","id":"1903.07609","version":1},"attestation_state":"computed","paper":{"title":"Multi-Differential Fairness Auditor for Black Box Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Huzefa Rangwala, Xavier Gitiaux","submitted_at":"2019-03-18T17:58:47Z","abstract_excerpt":"Machine learning algorithms are increasingly involved in sensitive decision-making process with adversarial implications on individuals. This paper presents mdfa, an approach that identifies the characteristics of the victims of a classifier's discrimination. We measure discrimination as a violation of multi-differential fairness. Multi-differential fairness is a guarantee that a black box classifier's outcomes do not leak information on the sensitive attributes of a small group of individuals. We reduce the problem of identifying worst-case violations to matching distributions and predicting "},"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":"1903.07609","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-18T17:58:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4d17b32d589e16a3e8328b482b632c0802e804751d194cd300e29654f0957b22","abstract_canon_sha256":"4e071c0605c9ae84125493011c02de59c79ddb1ee5efa7ab89f353f710c08567"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:00.873094Z","signature_b64":"qxW2675k8YCRJIXn8HPbT/SSawrYLBZ/mr5C1622eYzV8JsU7p1FvI0xBzBcDfcoFcTVLrjtgC+znG3FpkcqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a1626c57a6e343a7e772f5a1cddc5f3d58df5166530f4f9a6365499f16cbb4f","last_reissued_at":"2026-05-17T23:51:00.872499Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:00.872499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Differential Fairness Auditor for Black Box Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Huzefa Rangwala, Xavier Gitiaux","submitted_at":"2019-03-18T17:58:47Z","abstract_excerpt":"Machine learning algorithms are increasingly involved in sensitive decision-making process with adversarial implications on individuals. This paper presents mdfa, an approach that identifies the characteristics of the victims of a classifier's discrimination. We measure discrimination as a violation of multi-differential fairness. Multi-differential fairness is a guarantee that a black box classifier's outcomes do not leak information on the sensitive attributes of a small group of individuals. We reduce the problem of identifying worst-case violations to matching distributions and predicting "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.07609","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1903.07609","created_at":"2026-05-17T23:51:00.872598+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.07609v1","created_at":"2026-05-17T23:51:00.872598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.07609","created_at":"2026-05-17T23:51:00.872598+00:00"},{"alias_kind":"pith_short_12","alias_value":"TILCNRL2NY2D","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"TILCNRL2NY2DU7TX","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"TILCNRL2","created_at":"2026-05-18T12:33:27.125529+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/TILCNRL2NY2DU7TXF5NBZXOF6P","json":"https://pith.science/pith/TILCNRL2NY2DU7TXF5NBZXOF6P.json","graph_json":"https://pith.science/api/pith-number/TILCNRL2NY2DU7TXF5NBZXOF6P/graph.json","events_json":"https://pith.science/api/pith-number/TILCNRL2NY2DU7TXF5NBZXOF6P/events.json","paper":"https://pith.science/paper/TILCNRL2"},"agent_actions":{"view_html":"https://pith.science/pith/TILCNRL2NY2DU7TXF5NBZXOF6P","download_json":"https://pith.science/pith/TILCNRL2NY2DU7TXF5NBZXOF6P.json","view_paper":"https://pith.science/paper/TILCNRL2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.07609&json=true","fetch_graph":"https://pith.science/api/pith-number/TILCNRL2NY2DU7TXF5NBZXOF6P/graph.json","fetch_events":"https://pith.science/api/pith-number/TILCNRL2NY2DU7TXF5NBZXOF6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TILCNRL2NY2DU7TXF5NBZXOF6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TILCNRL2NY2DU7TXF5NBZXOF6P/action/storage_attestation","attest_author":"https://pith.science/pith/TILCNRL2NY2DU7TXF5NBZXOF6P/action/author_attestation","sign_citation":"https://pith.science/pith/TILCNRL2NY2DU7TXF5NBZXOF6P/action/citation_signature","submit_replication":"https://pith.science/pith/TILCNRL2NY2DU7TXF5NBZXOF6P/action/replication_record"}},"created_at":"2026-05-17T23:51:00.872598+00:00","updated_at":"2026-05-17T23:51:00.872598+00:00"}