{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HBCSONXODRW2MRQ2QFZI3JA4JU","short_pith_number":"pith:HBCSONXO","schema_version":"1.0","canonical_sha256":"38452736ee1c6da6461a81728da41c4d1ad89332ff040bd54b116ce7f537b541","source":{"kind":"arxiv","id":"2405.07393","version":1},"attestation_state":"computed","paper":{"title":"Intrinsic Fairness-Accuracy Tradeoffs under Equalized Odds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Meiyu Zhong, Ravi Tandon","submitted_at":"2024-05-12T23:15:21Z","abstract_excerpt":"With the growing adoption of machine learning (ML) systems in areas like law enforcement, criminal justice, finance, hiring, and admissions, it is increasingly critical to guarantee the fairness of decisions assisted by ML. In this paper, we study the tradeoff between fairness and accuracy under the statistical notion of equalized odds. We present a new upper bound on the accuracy (that holds for any classifier), as a function of the fairness budget. In addition, our bounds also exhibit dependence on the underlying statistics of the data, labels and the sensitive group attributes. We validate "},"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":"2405.07393","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-12T23:15:21Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"5c409427f29052636f24c9db14febbd4fed76c3ed147a677d49a572057a54c6b","abstract_canon_sha256":"de270571fa749c09d834855264888c9b01b554ce9f9668be572edd44fde94aec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:45.118346Z","signature_b64":"9k+J9RoXNyNLdwm7nG2pFFGfyhGB+L8Qp7tueIQJ9k+8huDP95fetoIxlJnkOJz2zTjRoSjzYpbboTme6GBkAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38452736ee1c6da6461a81728da41c4d1ad89332ff040bd54b116ce7f537b541","last_reissued_at":"2026-07-05T08:19:45.117869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:45.117869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intrinsic Fairness-Accuracy Tradeoffs under Equalized Odds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Meiyu Zhong, Ravi Tandon","submitted_at":"2024-05-12T23:15:21Z","abstract_excerpt":"With the growing adoption of machine learning (ML) systems in areas like law enforcement, criminal justice, finance, hiring, and admissions, it is increasingly critical to guarantee the fairness of decisions assisted by ML. In this paper, we study the tradeoff between fairness and accuracy under the statistical notion of equalized odds. We present a new upper bound on the accuracy (that holds for any classifier), as a function of the fairness budget. In addition, our bounds also exhibit dependence on the underlying statistics of the data, labels and the sensitive group attributes. We validate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.07393","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.07393/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":"2405.07393","created_at":"2026-07-05T08:19:45.117931+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.07393v1","created_at":"2026-07-05T08:19:45.117931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.07393","created_at":"2026-07-05T08:19:45.117931+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBCSONXODRW2","created_at":"2026-07-05T08:19:45.117931+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBCSONXODRW2MRQ2","created_at":"2026-07-05T08:19:45.117931+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBCSONXO","created_at":"2026-07-05T08:19:45.117931+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14424","citing_title":"Learning Fair Robustness via Domain Mixup","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HBCSONXODRW2MRQ2QFZI3JA4JU","json":"https://pith.science/pith/HBCSONXODRW2MRQ2QFZI3JA4JU.json","graph_json":"https://pith.science/api/pith-number/HBCSONXODRW2MRQ2QFZI3JA4JU/graph.json","events_json":"https://pith.science/api/pith-number/HBCSONXODRW2MRQ2QFZI3JA4JU/events.json","paper":"https://pith.science/paper/HBCSONXO"},"agent_actions":{"view_html":"https://pith.science/pith/HBCSONXODRW2MRQ2QFZI3JA4JU","download_json":"https://pith.science/pith/HBCSONXODRW2MRQ2QFZI3JA4JU.json","view_paper":"https://pith.science/paper/HBCSONXO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.07393&json=true","fetch_graph":"https://pith.science/api/pith-number/HBCSONXODRW2MRQ2QFZI3JA4JU/graph.json","fetch_events":"https://pith.science/api/pith-number/HBCSONXODRW2MRQ2QFZI3JA4JU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBCSONXODRW2MRQ2QFZI3JA4JU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBCSONXODRW2MRQ2QFZI3JA4JU/action/storage_attestation","attest_author":"https://pith.science/pith/HBCSONXODRW2MRQ2QFZI3JA4JU/action/author_attestation","sign_citation":"https://pith.science/pith/HBCSONXODRW2MRQ2QFZI3JA4JU/action/citation_signature","submit_replication":"https://pith.science/pith/HBCSONXODRW2MRQ2QFZI3JA4JU/action/replication_record"}},"created_at":"2026-07-05T08:19:45.117931+00:00","updated_at":"2026-07-05T08:19:45.117931+00:00"}