{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TPFDDQOFZRH5FU3TVTHE3KSXS6","short_pith_number":"pith:TPFDDQOF","schema_version":"1.0","canonical_sha256":"9bca31c1c5cc4fd2d373acce4daa579797b92734e3908ca556fb7b363a30c513","source":{"kind":"arxiv","id":"2311.01573","version":1},"attestation_state":"computed","paper":{"title":"Improving Fairness using Vision-Language Driven Image Augmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CV","authors_text":"Christos Tzelepis, Ioannis Patras, Moreno D'Inc\\`a, Nicu Sebe","submitted_at":"2023-11-02T19:51:10Z","abstract_excerpt":"Fairness is crucial when training a deep-learning discriminative model, especially in the facial domain. Models tend to correlate specific characteristics (such as age and skin color) with unrelated attributes (downstream tasks), resulting in biases which do not correspond to reality. It is common knowledge that these correlations are present in the data and are then transferred to the models during training. This paper proposes a method to mitigate these correlations to improve fairness. To do so, we learn interpretable and meaningful paths lying in the semantic space of a pre-trained diffusi"},"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":"2311.01573","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-02T19:51:10Z","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"title_canon_sha256":"12088d7966a1e5d64f434843c60c7443fd61556fa1bc38a035e7e36dd4ec77b2","abstract_canon_sha256":"7926c033d81dd02e61c02f6f5c857fc2b38369afdfc778ed039823f5631b106e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:31.333430Z","signature_b64":"K5ferzDGyut3hpG4bJoxy4rNHiqkKMntgesgtoCuIrimWBAAm9lZFQ4cj2+HY1z9c3q4QHn6FaPKtqOWIshRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bca31c1c5cc4fd2d373acce4daa579797b92734e3908ca556fb7b363a30c513","last_reissued_at":"2026-07-05T07:08:31.332941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:31.332941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Fairness using Vision-Language Driven Image Augmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CV","authors_text":"Christos Tzelepis, Ioannis Patras, Moreno D'Inc\\`a, Nicu Sebe","submitted_at":"2023-11-02T19:51:10Z","abstract_excerpt":"Fairness is crucial when training a deep-learning discriminative model, especially in the facial domain. Models tend to correlate specific characteristics (such as age and skin color) with unrelated attributes (downstream tasks), resulting in biases which do not correspond to reality. It is common knowledge that these correlations are present in the data and are then transferred to the models during training. This paper proposes a method to mitigate these correlations to improve fairness. To do so, we learn interpretable and meaningful paths lying in the semantic space of a pre-trained diffusi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01573","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/2311.01573/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":"2311.01573","created_at":"2026-07-05T07:08:31.333001+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.01573v1","created_at":"2026-07-05T07:08:31.333001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01573","created_at":"2026-07-05T07:08:31.333001+00:00"},{"alias_kind":"pith_short_12","alias_value":"TPFDDQOFZRH5","created_at":"2026-07-05T07:08:31.333001+00:00"},{"alias_kind":"pith_short_16","alias_value":"TPFDDQOFZRH5FU3T","created_at":"2026-07-05T07:08:31.333001+00:00"},{"alias_kind":"pith_short_8","alias_value":"TPFDDQOF","created_at":"2026-07-05T07:08:31.333001+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/TPFDDQOFZRH5FU3TVTHE3KSXS6","json":"https://pith.science/pith/TPFDDQOFZRH5FU3TVTHE3KSXS6.json","graph_json":"https://pith.science/api/pith-number/TPFDDQOFZRH5FU3TVTHE3KSXS6/graph.json","events_json":"https://pith.science/api/pith-number/TPFDDQOFZRH5FU3TVTHE3KSXS6/events.json","paper":"https://pith.science/paper/TPFDDQOF"},"agent_actions":{"view_html":"https://pith.science/pith/TPFDDQOFZRH5FU3TVTHE3KSXS6","download_json":"https://pith.science/pith/TPFDDQOFZRH5FU3TVTHE3KSXS6.json","view_paper":"https://pith.science/paper/TPFDDQOF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.01573&json=true","fetch_graph":"https://pith.science/api/pith-number/TPFDDQOFZRH5FU3TVTHE3KSXS6/graph.json","fetch_events":"https://pith.science/api/pith-number/TPFDDQOFZRH5FU3TVTHE3KSXS6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TPFDDQOFZRH5FU3TVTHE3KSXS6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TPFDDQOFZRH5FU3TVTHE3KSXS6/action/storage_attestation","attest_author":"https://pith.science/pith/TPFDDQOFZRH5FU3TVTHE3KSXS6/action/author_attestation","sign_citation":"https://pith.science/pith/TPFDDQOFZRH5FU3TVTHE3KSXS6/action/citation_signature","submit_replication":"https://pith.science/pith/TPFDDQOFZRH5FU3TVTHE3KSXS6/action/replication_record"}},"created_at":"2026-07-05T07:08:31.333001+00:00","updated_at":"2026-07-05T07:08:31.333001+00:00"}