{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XFOLYGE3KL6A4UTFXW54KGUQIH","short_pith_number":"pith:XFOLYGE3","schema_version":"1.0","canonical_sha256":"b95cbc189b52fc0e5265bdbbc51a9041c34a02f40cf04ce088584773552fa9f6","source":{"kind":"arxiv","id":"2106.03761","version":4},"attestation_state":"computed","paper":{"title":"FairCal: Fairness Calibration for Face Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Adam Oberman, Noah Marshall, Stephanie Cairns, Tiago Salvador, Vikram Voleti","submitted_at":"2021-06-07T16:26:26Z","abstract_excerpt":"Despite being widely used, face recognition models suffer from bias: the probability of a false positive (incorrect face match) strongly depends on sensitive attributes such as the ethnicity of the face. As a result, these models can disproportionately and negatively impact minority groups, particularly when used by law enforcement. The majority of bias reduction methods have several drawbacks: they use an end-to-end retraining approach, may not be feasible due to privacy issues, and often reduce accuracy. An alternative approach is post-processing methods that build fairer decision classifier"},"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":"2106.03761","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-07T16:26:26Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"244fde35eee31f822861a801669ba22119a4a22ed6eb57e4f534880a91e266a8","abstract_canon_sha256":"172a8a6ab383fa81aa424328d9a0eed11a83c0980fceb77fe74d945cb6ba2ed2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:56.816120Z","signature_b64":"bL187PsErTcLMnQ5jAIItS9rI28j7UGk6qSONRmrmHj6ebIAuSDnNygGB7OS4UXo7z5IoQY27tcwogpzfQQKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b95cbc189b52fc0e5265bdbbc51a9041c34a02f40cf04ce088584773552fa9f6","last_reissued_at":"2026-07-05T04:09:56.815656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:56.815656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FairCal: Fairness Calibration for Face Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Adam Oberman, Noah Marshall, Stephanie Cairns, Tiago Salvador, Vikram Voleti","submitted_at":"2021-06-07T16:26:26Z","abstract_excerpt":"Despite being widely used, face recognition models suffer from bias: the probability of a false positive (incorrect face match) strongly depends on sensitive attributes such as the ethnicity of the face. As a result, these models can disproportionately and negatively impact minority groups, particularly when used by law enforcement. The majority of bias reduction methods have several drawbacks: they use an end-to-end retraining approach, may not be feasible due to privacy issues, and often reduce accuracy. An alternative approach is post-processing methods that build fairer decision classifier"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03761","kind":"arxiv","version":4},"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/2106.03761/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":"2106.03761","created_at":"2026-07-05T04:09:56.815728+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03761v4","created_at":"2026-07-05T04:09:56.815728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03761","created_at":"2026-07-05T04:09:56.815728+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFOLYGE3KL6A","created_at":"2026-07-05T04:09:56.815728+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFOLYGE3KL6A4UTF","created_at":"2026-07-05T04:09:56.815728+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFOLYGE3","created_at":"2026-07-05T04:09:56.815728+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04469","citing_title":"Adaptive Calibration for Fair and Performant Facial Recognition","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XFOLYGE3KL6A4UTFXW54KGUQIH","json":"https://pith.science/pith/XFOLYGE3KL6A4UTFXW54KGUQIH.json","graph_json":"https://pith.science/api/pith-number/XFOLYGE3KL6A4UTFXW54KGUQIH/graph.json","events_json":"https://pith.science/api/pith-number/XFOLYGE3KL6A4UTFXW54KGUQIH/events.json","paper":"https://pith.science/paper/XFOLYGE3"},"agent_actions":{"view_html":"https://pith.science/pith/XFOLYGE3KL6A4UTFXW54KGUQIH","download_json":"https://pith.science/pith/XFOLYGE3KL6A4UTFXW54KGUQIH.json","view_paper":"https://pith.science/paper/XFOLYGE3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03761&json=true","fetch_graph":"https://pith.science/api/pith-number/XFOLYGE3KL6A4UTFXW54KGUQIH/graph.json","fetch_events":"https://pith.science/api/pith-number/XFOLYGE3KL6A4UTFXW54KGUQIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFOLYGE3KL6A4UTFXW54KGUQIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFOLYGE3KL6A4UTFXW54KGUQIH/action/storage_attestation","attest_author":"https://pith.science/pith/XFOLYGE3KL6A4UTFXW54KGUQIH/action/author_attestation","sign_citation":"https://pith.science/pith/XFOLYGE3KL6A4UTFXW54KGUQIH/action/citation_signature","submit_replication":"https://pith.science/pith/XFOLYGE3KL6A4UTFXW54KGUQIH/action/replication_record"}},"created_at":"2026-07-05T04:09:56.815728+00:00","updated_at":"2026-07-05T04:09:56.815728+00:00"}