{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:O7MGHLNWLSWEYUMYSNXVJG5A7S","short_pith_number":"pith:O7MGHLNW","schema_version":"1.0","canonical_sha256":"77d863adb65cac4c5198936f549ba0fcacaa4bcaf93cad3e84bb07b37adf468c","source":{"kind":"arxiv","id":"2304.14252","version":2},"attestation_state":"computed","paper":{"title":"FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associations","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christos Diou, Christos Koutlis, Ioannis Sarridis, Symeon Papadopoulos","submitted_at":"2023-04-27T15:10:46Z","abstract_excerpt":"Bias in computer vision systems can perpetuate or even amplify discrimination against certain populations. Considering that bias is often introduced by biased visual datasets, many recent research efforts focus on training fair models using such data. However, most of them heavily rely on the availability of protected attribute labels in the dataset, which limits their applicability, while label-unaware approaches, i.e., approaches operating without such labels, exhibit considerably lower performance. To overcome these limitations, this work introduces FLAC, a methodology that minimizes mutual"},"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":"2304.14252","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-27T15:10:46Z","cross_cats_sorted":[],"title_canon_sha256":"488c27dcc435cc7a4aa40ad076c8c4b681f7b7e832d3a19f0a4df1bdf2b4ce19","abstract_canon_sha256":"3d8b0d46fe10c314c7cbe1128f401ecd18fa369dbff4ee3732103fbfec8f3279"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:29.140481Z","signature_b64":"98lux3D7Z3a5csV8SWAPKL1uQR1CvI9AaTd5Xw69j+qeSvvoUOEW0enW0gg4hFXOG4tHLm/APQWEhl59QvbMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77d863adb65cac4c5198936f549ba0fcacaa4bcaf93cad3e84bb07b37adf468c","last_reissued_at":"2026-07-05T09:25:29.140067Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:29.140067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associations","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christos Diou, Christos Koutlis, Ioannis Sarridis, Symeon Papadopoulos","submitted_at":"2023-04-27T15:10:46Z","abstract_excerpt":"Bias in computer vision systems can perpetuate or even amplify discrimination against certain populations. Considering that bias is often introduced by biased visual datasets, many recent research efforts focus on training fair models using such data. However, most of them heavily rely on the availability of protected attribute labels in the dataset, which limits their applicability, while label-unaware approaches, i.e., approaches operating without such labels, exhibit considerably lower performance. To overcome these limitations, this work introduces FLAC, a methodology that minimizes mutual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14252","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/2304.14252/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":"2304.14252","created_at":"2026-07-05T09:25:29.140129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.14252v2","created_at":"2026-07-05T09:25:29.140129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14252","created_at":"2026-07-05T09:25:29.140129+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7MGHLNWLSWE","created_at":"2026-07-05T09:25:29.140129+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7MGHLNWLSWEYUMY","created_at":"2026-07-05T09:25:29.140129+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7MGHLNW","created_at":"2026-07-05T09:25:29.140129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.07313","citing_title":"FaceX: Understanding Face Attribute Classifiers through Summary Model Explanations","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O7MGHLNWLSWEYUMYSNXVJG5A7S","json":"https://pith.science/pith/O7MGHLNWLSWEYUMYSNXVJG5A7S.json","graph_json":"https://pith.science/api/pith-number/O7MGHLNWLSWEYUMYSNXVJG5A7S/graph.json","events_json":"https://pith.science/api/pith-number/O7MGHLNWLSWEYUMYSNXVJG5A7S/events.json","paper":"https://pith.science/paper/O7MGHLNW"},"agent_actions":{"view_html":"https://pith.science/pith/O7MGHLNWLSWEYUMYSNXVJG5A7S","download_json":"https://pith.science/pith/O7MGHLNWLSWEYUMYSNXVJG5A7S.json","view_paper":"https://pith.science/paper/O7MGHLNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.14252&json=true","fetch_graph":"https://pith.science/api/pith-number/O7MGHLNWLSWEYUMYSNXVJG5A7S/graph.json","fetch_events":"https://pith.science/api/pith-number/O7MGHLNWLSWEYUMYSNXVJG5A7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7MGHLNWLSWEYUMYSNXVJG5A7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7MGHLNWLSWEYUMYSNXVJG5A7S/action/storage_attestation","attest_author":"https://pith.science/pith/O7MGHLNWLSWEYUMYSNXVJG5A7S/action/author_attestation","sign_citation":"https://pith.science/pith/O7MGHLNWLSWEYUMYSNXVJG5A7S/action/citation_signature","submit_replication":"https://pith.science/pith/O7MGHLNWLSWEYUMYSNXVJG5A7S/action/replication_record"}},"created_at":"2026-07-05T09:25:29.140129+00:00","updated_at":"2026-07-05T09:25:29.140129+00:00"}