{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WHTQXOPPRYXVUKOAJPVLIAXQH7","short_pith_number":"pith:WHTQXOPP","schema_version":"1.0","canonical_sha256":"b1e70bb9ef8e2f5a29c04beab402f03fcac7b68cad3e5be819a66db6be6af51f","source":{"kind":"arxiv","id":"2403.14155","version":1},"attestation_state":"computed","paper":{"title":"Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image Customization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jimyeong Kim, Nojun Kwak, Wonhark Park, Wonjong Rhee, Wonsik Shin, Yeji Song","submitted_at":"2024-03-21T06:03:51Z","abstract_excerpt":"In a surge of text-to-image (T2I) models and their customization methods that generate new images of a user-provided subject, current works focus on alleviating the costs incurred by a lengthy per-subject optimization. These zero-shot customization methods encode the image of a specified subject into a visual embedding which is then utilized alongside the textual embedding for diffusion guidance. The visual embedding incorporates intrinsic information about the subject, while the textual embedding provides a new, transient context. However, the existing methods often 1) are significantly affec"},"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":"2403.14155","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T06:03:51Z","cross_cats_sorted":[],"title_canon_sha256":"f4b0179a03684c7b085dd9818ee68ae1a9d655e7a8aae3760e123682d3d000d2","abstract_canon_sha256":"ac831fa4e8fc7d6bd0a333d1ac86c534e0adb115fbcc9aeee77e7ccbbab49fdd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:55.275627Z","signature_b64":"5GSqQKVEdRAd0Tj0Qe3qkmvWOGIMUDoTZz9RcjUaBXZFGxrC/ESztW3F7x9OIxl3N81AofuF222guf3LHl60Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1e70bb9ef8e2f5a29c04beab402f03fcac7b68cad3e5be819a66db6be6af51f","last_reissued_at":"2026-07-05T07:58:55.275174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:55.275174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image Customization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jimyeong Kim, Nojun Kwak, Wonhark Park, Wonjong Rhee, Wonsik Shin, Yeji Song","submitted_at":"2024-03-21T06:03:51Z","abstract_excerpt":"In a surge of text-to-image (T2I) models and their customization methods that generate new images of a user-provided subject, current works focus on alleviating the costs incurred by a lengthy per-subject optimization. These zero-shot customization methods encode the image of a specified subject into a visual embedding which is then utilized alongside the textual embedding for diffusion guidance. The visual embedding incorporates intrinsic information about the subject, while the textual embedding provides a new, transient context. However, the existing methods often 1) are significantly affec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14155","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/2403.14155/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":"2403.14155","created_at":"2026-07-05T07:58:55.275224+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.14155v1","created_at":"2026-07-05T07:58:55.275224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14155","created_at":"2026-07-05T07:58:55.275224+00:00"},{"alias_kind":"pith_short_12","alias_value":"WHTQXOPPRYXV","created_at":"2026-07-05T07:58:55.275224+00:00"},{"alias_kind":"pith_short_16","alias_value":"WHTQXOPPRYXVUKOA","created_at":"2026-07-05T07:58:55.275224+00:00"},{"alias_kind":"pith_short_8","alias_value":"WHTQXOPP","created_at":"2026-07-05T07:58:55.275224+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02129","citing_title":"Equilibrated Diffusion: Frequency-aware Textual Embedding for Equilibrated Image Customization","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WHTQXOPPRYXVUKOAJPVLIAXQH7","json":"https://pith.science/pith/WHTQXOPPRYXVUKOAJPVLIAXQH7.json","graph_json":"https://pith.science/api/pith-number/WHTQXOPPRYXVUKOAJPVLIAXQH7/graph.json","events_json":"https://pith.science/api/pith-number/WHTQXOPPRYXVUKOAJPVLIAXQH7/events.json","paper":"https://pith.science/paper/WHTQXOPP"},"agent_actions":{"view_html":"https://pith.science/pith/WHTQXOPPRYXVUKOAJPVLIAXQH7","download_json":"https://pith.science/pith/WHTQXOPPRYXVUKOAJPVLIAXQH7.json","view_paper":"https://pith.science/paper/WHTQXOPP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.14155&json=true","fetch_graph":"https://pith.science/api/pith-number/WHTQXOPPRYXVUKOAJPVLIAXQH7/graph.json","fetch_events":"https://pith.science/api/pith-number/WHTQXOPPRYXVUKOAJPVLIAXQH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WHTQXOPPRYXVUKOAJPVLIAXQH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WHTQXOPPRYXVUKOAJPVLIAXQH7/action/storage_attestation","attest_author":"https://pith.science/pith/WHTQXOPPRYXVUKOAJPVLIAXQH7/action/author_attestation","sign_citation":"https://pith.science/pith/WHTQXOPPRYXVUKOAJPVLIAXQH7/action/citation_signature","submit_replication":"https://pith.science/pith/WHTQXOPPRYXVUKOAJPVLIAXQH7/action/replication_record"}},"created_at":"2026-07-05T07:58:55.275224+00:00","updated_at":"2026-07-05T07:58:55.275224+00:00"}