{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VYRGLCDCPA4FCUUITWZJD63YMA","short_pith_number":"pith:VYRGLCDC","schema_version":"1.0","canonical_sha256":"ae2265886278385152889db291fb78600c897e8d2b2c2e2e205969f4976cbd73","source":{"kind":"arxiv","id":"2304.07408","version":2},"attestation_state":"computed","paper":{"title":"Fairness in Visual Clustering: A Novel Transformer Clustering Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chi Nhan Duong, Hugh Churchill, Kaushik Roy, Khoa Luu, Marios Savvides, Xuan-Bac Nguyen","submitted_at":"2023-04-14T21:59:32Z","abstract_excerpt":"Promoting fairness for deep clustering models in unsupervised clustering settings to reduce demographic bias is a challenging goal. This is because of the limitation of large-scale balanced data with well-annotated labels for sensitive or protected attributes. In this paper, we first evaluate demographic bias in deep clustering models from the perspective of cluster purity, which is measured by the ratio of positive samples within a cluster to their correlation degree. This measurement is adopted as an indication of demographic bias. Then, a novel loss function is introduced to encourage a pur"},"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":"2304.07408","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-14T21:59:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5df0387797592c3c55b5ad03bec47fc17a15bed8b8f4560044626dba4420e6a1","abstract_canon_sha256":"6b2542f8af111b98a7f26bf141ccc5758e9bc4ea72a22942e1adf0ebc81c0ef7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:24.678379Z","signature_b64":"nAcIwpOMaGeUWbdC8gOWNVrWILAugxCnQ3BIdSp4/K0J8F5dCEoopN5FYY5ojnGUPp6hfJCdMJWSAC7Zm/6oDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae2265886278385152889db291fb78600c897e8d2b2c2e2e205969f4976cbd73","last_reissued_at":"2026-07-05T06:51:24.677846Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:24.677846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fairness in Visual Clustering: A Novel Transformer Clustering Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chi Nhan Duong, Hugh Churchill, Kaushik Roy, Khoa Luu, Marios Savvides, Xuan-Bac Nguyen","submitted_at":"2023-04-14T21:59:32Z","abstract_excerpt":"Promoting fairness for deep clustering models in unsupervised clustering settings to reduce demographic bias is a challenging goal. This is because of the limitation of large-scale balanced data with well-annotated labels for sensitive or protected attributes. In this paper, we first evaluate demographic bias in deep clustering models from the perspective of cluster purity, which is measured by the ratio of positive samples within a cluster to their correlation degree. This measurement is adopted as an indication of demographic bias. Then, a novel loss function is introduced to encourage a pur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.07408","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/2304.07408/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":"2304.07408","created_at":"2026-07-05T06:51:24.677904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.07408v2","created_at":"2026-07-05T06:51:24.677904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.07408","created_at":"2026-07-05T06:51:24.677904+00:00"},{"alias_kind":"pith_short_12","alias_value":"VYRGLCDCPA4F","created_at":"2026-07-05T06:51:24.677904+00:00"},{"alias_kind":"pith_short_16","alias_value":"VYRGLCDCPA4FCUUI","created_at":"2026-07-05T06:51:24.677904+00:00"},{"alias_kind":"pith_short_8","alias_value":"VYRGLCDC","created_at":"2026-07-05T06:51:24.677904+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.18187","citing_title":"BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VYRGLCDCPA4FCUUITWZJD63YMA","json":"https://pith.science/pith/VYRGLCDCPA4FCUUITWZJD63YMA.json","graph_json":"https://pith.science/api/pith-number/VYRGLCDCPA4FCUUITWZJD63YMA/graph.json","events_json":"https://pith.science/api/pith-number/VYRGLCDCPA4FCUUITWZJD63YMA/events.json","paper":"https://pith.science/paper/VYRGLCDC"},"agent_actions":{"view_html":"https://pith.science/pith/VYRGLCDCPA4FCUUITWZJD63YMA","download_json":"https://pith.science/pith/VYRGLCDCPA4FCUUITWZJD63YMA.json","view_paper":"https://pith.science/paper/VYRGLCDC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.07408&json=true","fetch_graph":"https://pith.science/api/pith-number/VYRGLCDCPA4FCUUITWZJD63YMA/graph.json","fetch_events":"https://pith.science/api/pith-number/VYRGLCDCPA4FCUUITWZJD63YMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VYRGLCDCPA4FCUUITWZJD63YMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VYRGLCDCPA4FCUUITWZJD63YMA/action/storage_attestation","attest_author":"https://pith.science/pith/VYRGLCDCPA4FCUUITWZJD63YMA/action/author_attestation","sign_citation":"https://pith.science/pith/VYRGLCDCPA4FCUUITWZJD63YMA/action/citation_signature","submit_replication":"https://pith.science/pith/VYRGLCDCPA4FCUUITWZJD63YMA/action/replication_record"}},"created_at":"2026-07-05T06:51:24.677904+00:00","updated_at":"2026-07-05T06:51:24.677904+00:00"}