{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2PLG7JF73IOSURNJX7TZWVPAAU","short_pith_number":"pith:2PLG7JF7","schema_version":"1.0","canonical_sha256":"d3d66fa4bfda1d2a45a9bfe79b55e00500c09182724d2a180141356e539bce28","source":{"kind":"arxiv","id":"2602.18831","version":2},"attestation_state":"computed","paper":{"title":"IDperturb: Enhancing Variation in Synthetic Face Generation via Angular Perturbation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eduarda Caldeira, Fadi Boutros, Naser Damer, Tahar Chettaoui","submitted_at":"2026-02-21T13:23:26Z","abstract_excerpt":"Synthetic data has emerged as a practical alternative to authentic face datasets for training face recognition (FR) systems, especially as privacy and legal concerns increasingly restrict the use of real biometric data. Recent advances in identity-conditional diffusion models have enabled the generation of photorealistic and identity-consistent face images. However, many of these models suffer from limited intra-class variation, an essential property for training robust and generalizable FR models. In this work, we propose IDPERTURB, a simple yet effective geometric-driven sampling strategy to"},"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":"2602.18831","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-21T13:23:26Z","cross_cats_sorted":[],"title_canon_sha256":"a872cbe469f347cb1601e874b3abf9967515dca8fa3be3bcd33b6ea70f45258e","abstract_canon_sha256":"18ff10c9dcf5d5b2c56413c60326c2298d64de54a6de3ddbd260745589b6548d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:51:28.973843Z","signature_b64":"YWS95C1Pib82a94HlYwTTvpDbUOPI1TNKl3S+UEH/6mJwOkuSN5GQIjfTE3gbW/pKTAIMz2BWZ8KRXN4dYyaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3d66fa4bfda1d2a45a9bfe79b55e00500c09182724d2a180141356e539bce28","last_reissued_at":"2026-08-07T00:51:28.971928Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:51:28.971928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IDperturb: Enhancing Variation in Synthetic Face Generation via Angular Perturbation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eduarda Caldeira, Fadi Boutros, Naser Damer, Tahar Chettaoui","submitted_at":"2026-02-21T13:23:26Z","abstract_excerpt":"Synthetic data has emerged as a practical alternative to authentic face datasets for training face recognition (FR) systems, especially as privacy and legal concerns increasingly restrict the use of real biometric data. Recent advances in identity-conditional diffusion models have enabled the generation of photorealistic and identity-consistent face images. However, many of these models suffer from limited intra-class variation, an essential property for training robust and generalizable FR models. In this work, we propose IDPERTURB, a simple yet effective geometric-driven sampling strategy to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.18831","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/2602.18831/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":"2602.18831","created_at":"2026-08-07T00:51:28.973628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.18831v2","created_at":"2026-08-07T00:51:28.973628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.18831","created_at":"2026-08-07T00:51:28.973628+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PLG7JF73IOS","created_at":"2026-08-07T00:51:28.973628+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PLG7JF73IOSURNJ","created_at":"2026-08-07T00:51:28.973628+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PLG7JF7","created_at":"2026-08-07T00:51:28.973628+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.30894","citing_title":"SteerFace: Debiasing Synthetic Face Generation via Adaptive Residue Perturbation","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2PLG7JF73IOSURNJX7TZWVPAAU","json":"https://pith.science/pith/2PLG7JF73IOSURNJX7TZWVPAAU.json","graph_json":"https://pith.science/api/pith-number/2PLG7JF73IOSURNJX7TZWVPAAU/graph.json","events_json":"https://pith.science/api/pith-number/2PLG7JF73IOSURNJX7TZWVPAAU/events.json","paper":"https://pith.science/paper/2PLG7JF7"},"agent_actions":{"view_html":"https://pith.science/pith/2PLG7JF73IOSURNJX7TZWVPAAU","download_json":"https://pith.science/pith/2PLG7JF73IOSURNJX7TZWVPAAU.json","view_paper":"https://pith.science/paper/2PLG7JF7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.18831&json=true","fetch_graph":"https://pith.science/api/pith-number/2PLG7JF73IOSURNJX7TZWVPAAU/graph.json","fetch_events":"https://pith.science/api/pith-number/2PLG7JF73IOSURNJX7TZWVPAAU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PLG7JF73IOSURNJX7TZWVPAAU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PLG7JF73IOSURNJX7TZWVPAAU/action/storage_attestation","attest_author":"https://pith.science/pith/2PLG7JF73IOSURNJX7TZWVPAAU/action/author_attestation","sign_citation":"https://pith.science/pith/2PLG7JF73IOSURNJX7TZWVPAAU/action/citation_signature","submit_replication":"https://pith.science/pith/2PLG7JF73IOSURNJX7TZWVPAAU/action/replication_record"}},"created_at":"2026-08-07T00:51:28.973628+00:00","updated_at":"2026-08-07T00:51:28.973628+00:00"}