{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NRJPKSRHM65U65RJI4JPIHU34H","short_pith_number":"pith:NRJPKSRH","schema_version":"1.0","canonical_sha256":"6c52f54a2767bb4f76294712f41e9be1fa4fc68ab0987e386e1df7b4a16103e8","source":{"kind":"arxiv","id":"2402.13061","version":1},"attestation_state":"computed","paper":{"title":"Toward Fairness via Maximum Mean Discrepancy Regularization on Logits Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ching-Hao Chiu, Hao-Wei Chung, Tsung-Yi Ho, Yiyu Shi, Yu-Jen Chen","submitted_at":"2024-02-20T14:56:28Z","abstract_excerpt":"Fairness has become increasingly pivotal in machine learning for high-risk applications such as machine learning in healthcare and facial recognition. However, we see the deficiency in the previous logits space constraint methods. Therefore, we propose a novel framework, Logits-MMD, that achieves the fairness condition by imposing constraints on output logits with Maximum Mean Discrepancy. Moreover, quantitative analysis and experimental results show that our framework has a better property that outperforms previous methods and achieves state-of-the-art on two facial recognition datasets and o"},"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":"2402.13061","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T14:56:28Z","cross_cats_sorted":[],"title_canon_sha256":"3e25c2d11d9b1b497f662a55792e12d352e3c6c3e8642ca4c3543ab54bd693b3","abstract_canon_sha256":"e009da31fc63b7926e23af257be90a061845a19c16f1f75f1b33e9a15725d304"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:20.319839Z","signature_b64":"VRDtVmQRbN5Nlr+FvPQ3t/aRGjJ1tOz6xRuEBVE9pVT+kwuCrO5TI0/LsXzpxpn1A5QWOobObILau1m5dxFmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c52f54a2767bb4f76294712f41e9be1fa4fc68ab0987e386e1df7b4a16103e8","last_reissued_at":"2026-07-05T07:47:20.319364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:20.319364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Fairness via Maximum Mean Discrepancy Regularization on Logits Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ching-Hao Chiu, Hao-Wei Chung, Tsung-Yi Ho, Yiyu Shi, Yu-Jen Chen","submitted_at":"2024-02-20T14:56:28Z","abstract_excerpt":"Fairness has become increasingly pivotal in machine learning for high-risk applications such as machine learning in healthcare and facial recognition. However, we see the deficiency in the previous logits space constraint methods. Therefore, we propose a novel framework, Logits-MMD, that achieves the fairness condition by imposing constraints on output logits with Maximum Mean Discrepancy. Moreover, quantitative analysis and experimental results show that our framework has a better property that outperforms previous methods and achieves state-of-the-art on two facial recognition datasets and o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13061","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/2402.13061/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":"2402.13061","created_at":"2026-07-05T07:47:20.319432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13061v1","created_at":"2026-07-05T07:47:20.319432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13061","created_at":"2026-07-05T07:47:20.319432+00:00"},{"alias_kind":"pith_short_12","alias_value":"NRJPKSRHM65U","created_at":"2026-07-05T07:47:20.319432+00:00"},{"alias_kind":"pith_short_16","alias_value":"NRJPKSRHM65U65RJ","created_at":"2026-07-05T07:47:20.319432+00:00"},{"alias_kind":"pith_short_8","alias_value":"NRJPKSRH","created_at":"2026-07-05T07:47:20.319432+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/NRJPKSRHM65U65RJI4JPIHU34H","json":"https://pith.science/pith/NRJPKSRHM65U65RJI4JPIHU34H.json","graph_json":"https://pith.science/api/pith-number/NRJPKSRHM65U65RJI4JPIHU34H/graph.json","events_json":"https://pith.science/api/pith-number/NRJPKSRHM65U65RJI4JPIHU34H/events.json","paper":"https://pith.science/paper/NRJPKSRH"},"agent_actions":{"view_html":"https://pith.science/pith/NRJPKSRHM65U65RJI4JPIHU34H","download_json":"https://pith.science/pith/NRJPKSRHM65U65RJI4JPIHU34H.json","view_paper":"https://pith.science/paper/NRJPKSRH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13061&json=true","fetch_graph":"https://pith.science/api/pith-number/NRJPKSRHM65U65RJI4JPIHU34H/graph.json","fetch_events":"https://pith.science/api/pith-number/NRJPKSRHM65U65RJI4JPIHU34H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NRJPKSRHM65U65RJI4JPIHU34H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NRJPKSRHM65U65RJI4JPIHU34H/action/storage_attestation","attest_author":"https://pith.science/pith/NRJPKSRHM65U65RJI4JPIHU34H/action/author_attestation","sign_citation":"https://pith.science/pith/NRJPKSRHM65U65RJI4JPIHU34H/action/citation_signature","submit_replication":"https://pith.science/pith/NRJPKSRHM65U65RJI4JPIHU34H/action/replication_record"}},"created_at":"2026-07-05T07:47:20.319432+00:00","updated_at":"2026-07-05T07:47:20.319432+00:00"}