{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZKO2BPQ42WRWKKO5VRABXMZSNP","short_pith_number":"pith:ZKO2BPQ4","schema_version":"1.0","canonical_sha256":"ca9da0be1cd5a36529ddac401bb3326bd10dd47db9e5c54dfa7a9fd544b062c5","source":{"kind":"arxiv","id":"2506.23033","version":2},"attestation_state":"computed","paper":{"title":"How Reliable are Fairness Audits with Unreliable Data?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Yash Vardhan Tomar","submitted_at":"2025-06-28T23:12:59Z","abstract_excerpt":"Fairness audits are a key component of responsible machine-learning deployment. Yet, the reliability of audit recommendations under incomplete protected-label access is still poorly understood. In this work, we focused on protected-label missingness in fairness mitigation audits. We introduced a seed-calibrated stress test to separate missingness effects from seed-to-seed movement that is already present under complete labels. Across ACS/Folktables tasks, we found that positive-availability missingness usually does not move selected mitigation methods beyond the complete-label seed floor. The "},"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":"2506.23033","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-28T23:12:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"82f825bb99fb3e5eeaef7372816f5989bc2f81874f414a13ce35f6b7562bba7b","abstract_canon_sha256":"dee31d3e522e1b49754d9c4f1015a4b07882267d0519c98ca98b9eea348d36e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:38.890550Z","signature_b64":"PtCxRRl37/NbIhTK6QXte/cU//mSnof0Ik1SA/e/AjXLpQ7aB2QSuOHf6Fxf2PoPoAcOHYBCnLEiJQUXDbxZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca9da0be1cd5a36529ddac401bb3326bd10dd47db9e5c54dfa7a9fd544b062c5","last_reissued_at":"2026-06-09T01:04:38.890083Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:38.890083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Reliable are Fairness Audits with Unreliable Data?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Yash Vardhan Tomar","submitted_at":"2025-06-28T23:12:59Z","abstract_excerpt":"Fairness audits are a key component of responsible machine-learning deployment. Yet, the reliability of audit recommendations under incomplete protected-label access is still poorly understood. In this work, we focused on protected-label missingness in fairness mitigation audits. We introduced a seed-calibrated stress test to separate missingness effects from seed-to-seed movement that is already present under complete labels. Across ACS/Folktables tasks, we found that positive-availability missingness usually does not move selected mitigation methods beyond the complete-label seed floor. The "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23033","kind":"arxiv","version":2},"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/2506.23033/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":"2506.23033","created_at":"2026-06-09T01:04:38.890142+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23033v2","created_at":"2026-06-09T01:04:38.890142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23033","created_at":"2026-06-09T01:04:38.890142+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKO2BPQ42WRW","created_at":"2026-06-09T01:04:38.890142+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKO2BPQ42WRWKKO5","created_at":"2026-06-09T01:04:38.890142+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKO2BPQ4","created_at":"2026-06-09T01:04:38.890142+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/ZKO2BPQ42WRWKKO5VRABXMZSNP","json":"https://pith.science/pith/ZKO2BPQ42WRWKKO5VRABXMZSNP.json","graph_json":"https://pith.science/api/pith-number/ZKO2BPQ42WRWKKO5VRABXMZSNP/graph.json","events_json":"https://pith.science/api/pith-number/ZKO2BPQ42WRWKKO5VRABXMZSNP/events.json","paper":"https://pith.science/paper/ZKO2BPQ4"},"agent_actions":{"view_html":"https://pith.science/pith/ZKO2BPQ42WRWKKO5VRABXMZSNP","download_json":"https://pith.science/pith/ZKO2BPQ42WRWKKO5VRABXMZSNP.json","view_paper":"https://pith.science/paper/ZKO2BPQ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23033&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKO2BPQ42WRWKKO5VRABXMZSNP/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKO2BPQ42WRWKKO5VRABXMZSNP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKO2BPQ42WRWKKO5VRABXMZSNP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKO2BPQ42WRWKKO5VRABXMZSNP/action/storage_attestation","attest_author":"https://pith.science/pith/ZKO2BPQ42WRWKKO5VRABXMZSNP/action/author_attestation","sign_citation":"https://pith.science/pith/ZKO2BPQ42WRWKKO5VRABXMZSNP/action/citation_signature","submit_replication":"https://pith.science/pith/ZKO2BPQ42WRWKKO5VRABXMZSNP/action/replication_record"}},"created_at":"2026-06-09T01:04:38.890142+00:00","updated_at":"2026-06-09T01:04:38.890142+00:00"}