{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WUUTGLN535Q2LNZ4UPWSKHP7LL","short_pith_number":"pith:WUUTGLN5","schema_version":"1.0","canonical_sha256":"b529332dbddf61a5b73ca3ed251dff5af0a762ba2d26f197b4093a6da1f19319","source":{"kind":"arxiv","id":"2312.15905","version":1},"attestation_state":"computed","paper":{"title":"Cross Initialization for Personalized Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Xie, Jian Yin, Lianyu Pang, Qing Li, Qiping Wang, Xudong Mao","submitted_at":"2023-12-26T06:49:53Z","abstract_excerpt":"Recently, there has been a surge in face personalization techniques, benefiting from the advanced capabilities of pretrained text-to-image diffusion models. Among these, a notable method is Textual Inversion, which generates personalized images by inverting given images into textual embeddings. However, methods based on Textual Inversion still struggle with balancing the trade-off between reconstruction quality and editability. In this study, we examine this issue through the lens of initialization. Upon closely examining traditional initialization methods, we identified a significant disparit"},"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":"2312.15905","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-26T06:49:53Z","cross_cats_sorted":[],"title_canon_sha256":"23c7a54f164f393145efae60a1d26ce050cf0af1527eb150d33a37989c32491f","abstract_canon_sha256":"69606ede1e1ab68a9e3262bcc0c127bdfd31a9f65c31300969f7a9d58e2c3f63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:03.270038Z","signature_b64":"ZROzK0DZdS0Unv2T3DuREANcIjbRuTmGxI1hAG4+5gPB3hsDvEf5j56kDWCIybJOjh/QwbsK6hFMB/StGT5ECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b529332dbddf61a5b73ca3ed251dff5af0a762ba2d26f197b4093a6da1f19319","last_reissued_at":"2026-07-05T07:28:03.269569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:03.269569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross Initialization for Personalized Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Xie, Jian Yin, Lianyu Pang, Qing Li, Qiping Wang, Xudong Mao","submitted_at":"2023-12-26T06:49:53Z","abstract_excerpt":"Recently, there has been a surge in face personalization techniques, benefiting from the advanced capabilities of pretrained text-to-image diffusion models. Among these, a notable method is Textual Inversion, which generates personalized images by inverting given images into textual embeddings. However, methods based on Textual Inversion still struggle with balancing the trade-off between reconstruction quality and editability. In this study, we examine this issue through the lens of initialization. Upon closely examining traditional initialization methods, we identified a significant disparit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15905","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/2312.15905/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":"2312.15905","created_at":"2026-07-05T07:28:03.269626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.15905v1","created_at":"2026-07-05T07:28:03.269626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15905","created_at":"2026-07-05T07:28:03.269626+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUUTGLN535Q2","created_at":"2026-07-05T07:28:03.269626+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUUTGLN535Q2LNZ4","created_at":"2026-07-05T07:28:03.269626+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUUTGLN5","created_at":"2026-07-05T07:28:03.269626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18068","citing_title":"PersonaCraft: Personalized and Controllable Full-Body Multi-Human Scene Generation Using Occlusion-Aware 3D-Conditioned Diffusion","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WUUTGLN535Q2LNZ4UPWSKHP7LL","json":"https://pith.science/pith/WUUTGLN535Q2LNZ4UPWSKHP7LL.json","graph_json":"https://pith.science/api/pith-number/WUUTGLN535Q2LNZ4UPWSKHP7LL/graph.json","events_json":"https://pith.science/api/pith-number/WUUTGLN535Q2LNZ4UPWSKHP7LL/events.json","paper":"https://pith.science/paper/WUUTGLN5"},"agent_actions":{"view_html":"https://pith.science/pith/WUUTGLN535Q2LNZ4UPWSKHP7LL","download_json":"https://pith.science/pith/WUUTGLN535Q2LNZ4UPWSKHP7LL.json","view_paper":"https://pith.science/paper/WUUTGLN5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.15905&json=true","fetch_graph":"https://pith.science/api/pith-number/WUUTGLN535Q2LNZ4UPWSKHP7LL/graph.json","fetch_events":"https://pith.science/api/pith-number/WUUTGLN535Q2LNZ4UPWSKHP7LL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUUTGLN535Q2LNZ4UPWSKHP7LL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUUTGLN535Q2LNZ4UPWSKHP7LL/action/storage_attestation","attest_author":"https://pith.science/pith/WUUTGLN535Q2LNZ4UPWSKHP7LL/action/author_attestation","sign_citation":"https://pith.science/pith/WUUTGLN535Q2LNZ4UPWSKHP7LL/action/citation_signature","submit_replication":"https://pith.science/pith/WUUTGLN535Q2LNZ4UPWSKHP7LL/action/replication_record"}},"created_at":"2026-07-05T07:28:03.269626+00:00","updated_at":"2026-07-05T07:28:03.269626+00:00"}