{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YDYGSQQEH7DCW4W2YPVO2G5LBI","short_pith_number":"pith:YDYGSQQE","schema_version":"1.0","canonical_sha256":"c0f06942043fc62b72dac3eaed1bab0a319e4618e4e95e420a94e3cebe1d6f81","source":{"kind":"arxiv","id":"2312.11826","version":1},"attestation_state":"computed","paper":{"title":"Decoupled Textual Embeddings for Customized Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hu Han, Jinfeng Bai, Wangmeng Zuo, Yufei Cai, Yuxiang Wei, Zhilong Ji","submitted_at":"2023-12-19T03:32:10Z","abstract_excerpt":"Customized text-to-image generation, which aims to learn user-specified concepts with a few images, has drawn significant attention recently. However, existing methods usually suffer from overfitting issues and entangle the subject-unrelated information (e.g., background and pose) with the learned concept, limiting the potential to compose concept into new scenes. To address these issues, we propose the DETEX, a novel approach that learns the disentangled concept embedding for flexible customized text-to-image generation. Unlike conventional methods that learn a single concept embedding from t"},"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":"2312.11826","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T03:32:10Z","cross_cats_sorted":[],"title_canon_sha256":"155a597d13debfccf7fc66ec74425637073e55cb55699250db3a31a9c61f0c62","abstract_canon_sha256":"f6b514e248bf7a241789cd24990077174e68d65cddddb1281ae9976cf302cdeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:54.972006Z","signature_b64":"A79vYWIlHqJ2QHVKgMi5HogtUDQ7l3Ri/Gn4n1Tmm6dEsj0GXUXPAwD/U4jXxJ6unvgDFVc9OBBYV9DJ7tTIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0f06942043fc62b72dac3eaed1bab0a319e4618e4e95e420a94e3cebe1d6f81","last_reissued_at":"2026-07-05T07:25:54.971489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:54.971489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupled Textual Embeddings for Customized Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hu Han, Jinfeng Bai, Wangmeng Zuo, Yufei Cai, Yuxiang Wei, Zhilong Ji","submitted_at":"2023-12-19T03:32:10Z","abstract_excerpt":"Customized text-to-image generation, which aims to learn user-specified concepts with a few images, has drawn significant attention recently. However, existing methods usually suffer from overfitting issues and entangle the subject-unrelated information (e.g., background and pose) with the learned concept, limiting the potential to compose concept into new scenes. To address these issues, we propose the DETEX, a novel approach that learns the disentangled concept embedding for flexible customized text-to-image generation. Unlike conventional methods that learn a single concept embedding from t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11826","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/2312.11826/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":"2312.11826","created_at":"2026-07-05T07:25:54.971549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.11826v1","created_at":"2026-07-05T07:25:54.971549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11826","created_at":"2026-07-05T07:25:54.971549+00:00"},{"alias_kind":"pith_short_12","alias_value":"YDYGSQQEH7DC","created_at":"2026-07-05T07:25:54.971549+00:00"},{"alias_kind":"pith_short_16","alias_value":"YDYGSQQEH7DCW4W2","created_at":"2026-07-05T07:25:54.971549+00:00"},{"alias_kind":"pith_short_8","alias_value":"YDYGSQQE","created_at":"2026-07-05T07:25:54.971549+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.05501","citing_title":"Preliminary Explorations with GPT-4o(mni) Native Image Generation","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YDYGSQQEH7DCW4W2YPVO2G5LBI","json":"https://pith.science/pith/YDYGSQQEH7DCW4W2YPVO2G5LBI.json","graph_json":"https://pith.science/api/pith-number/YDYGSQQEH7DCW4W2YPVO2G5LBI/graph.json","events_json":"https://pith.science/api/pith-number/YDYGSQQEH7DCW4W2YPVO2G5LBI/events.json","paper":"https://pith.science/paper/YDYGSQQE"},"agent_actions":{"view_html":"https://pith.science/pith/YDYGSQQEH7DCW4W2YPVO2G5LBI","download_json":"https://pith.science/pith/YDYGSQQEH7DCW4W2YPVO2G5LBI.json","view_paper":"https://pith.science/paper/YDYGSQQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.11826&json=true","fetch_graph":"https://pith.science/api/pith-number/YDYGSQQEH7DCW4W2YPVO2G5LBI/graph.json","fetch_events":"https://pith.science/api/pith-number/YDYGSQQEH7DCW4W2YPVO2G5LBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YDYGSQQEH7DCW4W2YPVO2G5LBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YDYGSQQEH7DCW4W2YPVO2G5LBI/action/storage_attestation","attest_author":"https://pith.science/pith/YDYGSQQEH7DCW4W2YPVO2G5LBI/action/author_attestation","sign_citation":"https://pith.science/pith/YDYGSQQEH7DCW4W2YPVO2G5LBI/action/citation_signature","submit_replication":"https://pith.science/pith/YDYGSQQEH7DCW4W2YPVO2G5LBI/action/replication_record"}},"created_at":"2026-07-05T07:25:54.971549+00:00","updated_at":"2026-07-05T07:25:54.971549+00:00"}