{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SN2DBTIH6BULNFTJUMZC5MQXCL","short_pith_number":"pith:SN2DBTIH","schema_version":"1.0","canonical_sha256":"937430cd07f068b69669a3322eb21712ec9eae89aa7f1c5ffb42a258c5c5dc21","source":{"kind":"arxiv","id":"2503.14138","version":1},"attestation_state":"computed","paper":{"title":"Exploring Disparity-Accuracy Trade-offs in Face Recognition Systems: The Role of Datasets, Architectures, and Loss Functions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CV","authors_text":"Animesh Mukherjee, Sagnik Basu, Sandipan Sikdar, Siddharth D Jaiswal","submitted_at":"2025-03-18T11:04:57Z","abstract_excerpt":"Automated Face Recognition Systems (FRSs), developed using deep learning models, are deployed worldwide for identity verification and facial attribute analysis. The performance of these models is determined by a complex interdependence among the model architecture, optimization/loss function and datasets. Although FRSs have surpassed human-level accuracy, they continue to be disparate against certain demographics. Due to the ubiquity of applications, it is extremely important to understand the impact of the three components -- model architecture, loss function and face image dataset on the acc"},"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":"2503.14138","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T11:04:57Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"d06c49487a1e766d980f9d9c8d492a68e4cb0ed82a9b11d312052e84a7a17836","abstract_canon_sha256":"0f4955d24ac081fdac2d10d31e1c4281f9a63f141aabb94c3d966dc3dc122de5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:55.956984Z","signature_b64":"Jv6v6bsUOEEjFplKS2Ju358Z6JS3TS0aO+8ATmcVoi77hR4ahWEbkEQ7gIS1yKwYnaNccdByOdauUgBgSZzaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"937430cd07f068b69669a3322eb21712ec9eae89aa7f1c5ffb42a258c5c5dc21","last_reissued_at":"2026-07-05T10:33:55.955710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:55.955710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Disparity-Accuracy Trade-offs in Face Recognition Systems: The Role of Datasets, Architectures, and Loss Functions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CV","authors_text":"Animesh Mukherjee, Sagnik Basu, Sandipan Sikdar, Siddharth D Jaiswal","submitted_at":"2025-03-18T11:04:57Z","abstract_excerpt":"Automated Face Recognition Systems (FRSs), developed using deep learning models, are deployed worldwide for identity verification and facial attribute analysis. The performance of these models is determined by a complex interdependence among the model architecture, optimization/loss function and datasets. Although FRSs have surpassed human-level accuracy, they continue to be disparate against certain demographics. Due to the ubiquity of applications, it is extremely important to understand the impact of the three components -- model architecture, loss function and face image dataset on the acc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14138","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/2503.14138/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":"2503.14138","created_at":"2026-07-05T10:33:55.955835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.14138v1","created_at":"2026-07-05T10:33:55.955835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14138","created_at":"2026-07-05T10:33:55.955835+00:00"},{"alias_kind":"pith_short_12","alias_value":"SN2DBTIH6BUL","created_at":"2026-07-05T10:33:55.955835+00:00"},{"alias_kind":"pith_short_16","alias_value":"SN2DBTIH6BULNFTJ","created_at":"2026-07-05T10:33:55.955835+00:00"},{"alias_kind":"pith_short_8","alias_value":"SN2DBTIH","created_at":"2026-07-05T10:33:55.955835+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/SN2DBTIH6BULNFTJUMZC5MQXCL","json":"https://pith.science/pith/SN2DBTIH6BULNFTJUMZC5MQXCL.json","graph_json":"https://pith.science/api/pith-number/SN2DBTIH6BULNFTJUMZC5MQXCL/graph.json","events_json":"https://pith.science/api/pith-number/SN2DBTIH6BULNFTJUMZC5MQXCL/events.json","paper":"https://pith.science/paper/SN2DBTIH"},"agent_actions":{"view_html":"https://pith.science/pith/SN2DBTIH6BULNFTJUMZC5MQXCL","download_json":"https://pith.science/pith/SN2DBTIH6BULNFTJUMZC5MQXCL.json","view_paper":"https://pith.science/paper/SN2DBTIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.14138&json=true","fetch_graph":"https://pith.science/api/pith-number/SN2DBTIH6BULNFTJUMZC5MQXCL/graph.json","fetch_events":"https://pith.science/api/pith-number/SN2DBTIH6BULNFTJUMZC5MQXCL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SN2DBTIH6BULNFTJUMZC5MQXCL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SN2DBTIH6BULNFTJUMZC5MQXCL/action/storage_attestation","attest_author":"https://pith.science/pith/SN2DBTIH6BULNFTJUMZC5MQXCL/action/author_attestation","sign_citation":"https://pith.science/pith/SN2DBTIH6BULNFTJUMZC5MQXCL/action/citation_signature","submit_replication":"https://pith.science/pith/SN2DBTIH6BULNFTJUMZC5MQXCL/action/replication_record"}},"created_at":"2026-07-05T10:33:55.955835+00:00","updated_at":"2026-07-05T10:33:55.955835+00:00"}