{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RTIF66PKHGSSE7YXRQRF4G4TCM","short_pith_number":"pith:RTIF66PK","schema_version":"1.0","canonical_sha256":"8cd05f79ea39a5227f178c225e1b931303001ce9d320e72f503dffba2c7d36ef","source":{"kind":"arxiv","id":"2311.04315","version":4},"attestation_state":"computed","paper":{"title":"A Data Perspective on Enhanced Identity Preservation for Diffusion Personalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Helge Rhodin, Kun Wan, Lantao Yu, Nicholas Kolkin, Ratheesh Kalarot, Xingzhe He, Zhiwen Cao","submitted_at":"2023-11-07T19:41:19Z","abstract_excerpt":"Large text-to-image models have revolutionized the ability to generate imagery using natural language. However, particularly unique or personal visual concepts, such as pets and furniture, will not be captured by the original model. This has led to interest in how to personalize a text-to-image model. Despite significant progress, this task remains a formidable challenge, particularly in preserving the subject's identity. Most researchers attempt to address this issue by modifying model architectures. These methods are capable of keeping the subject structure and color but fail to preserve ide"},"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":"2311.04315","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-07T19:41:19Z","cross_cats_sorted":[],"title_canon_sha256":"56cf88c0b290abaec62582c3721792fc1625df7dc2c85ac2b6a4f004801d84aa","abstract_canon_sha256":"2d91a56edfd57057d99e0b064cf189938aee6dd9fbd4856906c35c1fa2560448"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:42.532825Z","signature_b64":"qJhlQs9fm2aRKkAAfSv26+FWjlABxH7wrmIWYFsqVYQlj6U1IXtiVEHBEwRN6cnx8+G5za+d73zzlTeQE/+/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cd05f79ea39a5227f178c225e1b931303001ce9d320e72f503dffba2c7d36ef","last_reissued_at":"2026-07-05T09:31:42.532292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:42.532292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Data Perspective on Enhanced Identity Preservation for Diffusion Personalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Helge Rhodin, Kun Wan, Lantao Yu, Nicholas Kolkin, Ratheesh Kalarot, Xingzhe He, Zhiwen Cao","submitted_at":"2023-11-07T19:41:19Z","abstract_excerpt":"Large text-to-image models have revolutionized the ability to generate imagery using natural language. However, particularly unique or personal visual concepts, such as pets and furniture, will not be captured by the original model. This has led to interest in how to personalize a text-to-image model. Despite significant progress, this task remains a formidable challenge, particularly in preserving the subject's identity. Most researchers attempt to address this issue by modifying model architectures. These methods are capable of keeping the subject structure and color but fail to preserve ide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04315","kind":"arxiv","version":4},"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/2311.04315/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":"2311.04315","created_at":"2026-07-05T09:31:42.532357+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.04315v4","created_at":"2026-07-05T09:31:42.532357+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04315","created_at":"2026-07-05T09:31:42.532357+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTIF66PKHGSS","created_at":"2026-07-05T09:31:42.532357+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTIF66PKHGSSE7YX","created_at":"2026-07-05T09:31:42.532357+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTIF66PK","created_at":"2026-07-05T09:31:42.532357+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.08248","citing_title":"TextBoost: Boosting Text Encoder for Personalized Text-to-Image Generation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTIF66PKHGSSE7YXRQRF4G4TCM","json":"https://pith.science/pith/RTIF66PKHGSSE7YXRQRF4G4TCM.json","graph_json":"https://pith.science/api/pith-number/RTIF66PKHGSSE7YXRQRF4G4TCM/graph.json","events_json":"https://pith.science/api/pith-number/RTIF66PKHGSSE7YXRQRF4G4TCM/events.json","paper":"https://pith.science/paper/RTIF66PK"},"agent_actions":{"view_html":"https://pith.science/pith/RTIF66PKHGSSE7YXRQRF4G4TCM","download_json":"https://pith.science/pith/RTIF66PKHGSSE7YXRQRF4G4TCM.json","view_paper":"https://pith.science/paper/RTIF66PK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.04315&json=true","fetch_graph":"https://pith.science/api/pith-number/RTIF66PKHGSSE7YXRQRF4G4TCM/graph.json","fetch_events":"https://pith.science/api/pith-number/RTIF66PKHGSSE7YXRQRF4G4TCM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTIF66PKHGSSE7YXRQRF4G4TCM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTIF66PKHGSSE7YXRQRF4G4TCM/action/storage_attestation","attest_author":"https://pith.science/pith/RTIF66PKHGSSE7YXRQRF4G4TCM/action/author_attestation","sign_citation":"https://pith.science/pith/RTIF66PKHGSSE7YXRQRF4G4TCM/action/citation_signature","submit_replication":"https://pith.science/pith/RTIF66PKHGSSE7YXRQRF4G4TCM/action/replication_record"}},"created_at":"2026-07-05T09:31:42.532357+00:00","updated_at":"2026-07-05T09:31:42.532357+00:00"}