{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KEHKVZJWT37TFCP3VZK7CMKC7J","short_pith_number":"pith:KEHKVZJW","schema_version":"1.0","canonical_sha256":"510eaae5369eff3289fbae55f13142fa64ea90d8449d6431e48f9d48ae09e62b","source":{"kind":"arxiv","id":"2504.14202","version":3},"attestation_state":"computed","paper":{"title":"Learning Joint ID-Textual Representation for ID-Preserving Image Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hao Kang, Liming Jiang, Qing Yan, Xin Lu, Yumin Jia, Zichuan Liu","submitted_at":"2025-04-19T06:31:07Z","abstract_excerpt":"We propose a novel framework for ID-preserving generation using a multi-modal encoding strategy rather than injecting identity features via adapters into pre-trained models. Our method treats identity and text as a unified conditioning input. To achieve this, we introduce FaceCLIP, a multi-modal encoder that learns a joint embedding space for both identity and textual semantics. Given a reference face and a text prompt, FaceCLIP produces a unified representation that encodes both identity and text, which conditions a base diffusion model to generate images that are identity-consistent and text"},"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":"2504.14202","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-19T06:31:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a3a7024154c1bbf8f9de2a609b1b45d3de6eb8d1489383bcbbd3ecca046c2d4e","abstract_canon_sha256":"fc142ac0ef9799b1c157f16b9121e78f17e87dc2c17e74aa2ba2caa0eea35931"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:23.733493Z","signature_b64":"fBp8Ms8S2qDbtynF5Iiv5TtcaN3ngqyvv4e0qWTYjbAlmLawgvdVg0Nq7lsdt+YE/sN0pYP/dO6srJrS9Xd0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"510eaae5369eff3289fbae55f13142fa64ea90d8449d6431e48f9d48ae09e62b","last_reissued_at":"2026-07-05T11:07:23.732996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:23.732996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Joint ID-Textual Representation for ID-Preserving Image Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hao Kang, Liming Jiang, Qing Yan, Xin Lu, Yumin Jia, Zichuan Liu","submitted_at":"2025-04-19T06:31:07Z","abstract_excerpt":"We propose a novel framework for ID-preserving generation using a multi-modal encoding strategy rather than injecting identity features via adapters into pre-trained models. Our method treats identity and text as a unified conditioning input. To achieve this, we introduce FaceCLIP, a multi-modal encoder that learns a joint embedding space for both identity and textual semantics. Given a reference face and a text prompt, FaceCLIP produces a unified representation that encodes both identity and text, which conditions a base diffusion model to generate images that are identity-consistent and text"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14202","kind":"arxiv","version":3},"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/2504.14202/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":"2504.14202","created_at":"2026-07-05T11:07:23.733051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14202v3","created_at":"2026-07-05T11:07:23.733051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14202","created_at":"2026-07-05T11:07:23.733051+00:00"},{"alias_kind":"pith_short_12","alias_value":"KEHKVZJWT37T","created_at":"2026-07-05T11:07:23.733051+00:00"},{"alias_kind":"pith_short_16","alias_value":"KEHKVZJWT37TFCP3","created_at":"2026-07-05T11:07:23.733051+00:00"},{"alias_kind":"pith_short_8","alias_value":"KEHKVZJW","created_at":"2026-07-05T11:07:23.733051+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KEHKVZJWT37TFCP3VZK7CMKC7J","json":"https://pith.science/pith/KEHKVZJWT37TFCP3VZK7CMKC7J.json","graph_json":"https://pith.science/api/pith-number/KEHKVZJWT37TFCP3VZK7CMKC7J/graph.json","events_json":"https://pith.science/api/pith-number/KEHKVZJWT37TFCP3VZK7CMKC7J/events.json","paper":"https://pith.science/paper/KEHKVZJW"},"agent_actions":{"view_html":"https://pith.science/pith/KEHKVZJWT37TFCP3VZK7CMKC7J","download_json":"https://pith.science/pith/KEHKVZJWT37TFCP3VZK7CMKC7J.json","view_paper":"https://pith.science/paper/KEHKVZJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14202&json=true","fetch_graph":"https://pith.science/api/pith-number/KEHKVZJWT37TFCP3VZK7CMKC7J/graph.json","fetch_events":"https://pith.science/api/pith-number/KEHKVZJWT37TFCP3VZK7CMKC7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KEHKVZJWT37TFCP3VZK7CMKC7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KEHKVZJWT37TFCP3VZK7CMKC7J/action/storage_attestation","attest_author":"https://pith.science/pith/KEHKVZJWT37TFCP3VZK7CMKC7J/action/author_attestation","sign_citation":"https://pith.science/pith/KEHKVZJWT37TFCP3VZK7CMKC7J/action/citation_signature","submit_replication":"https://pith.science/pith/KEHKVZJWT37TFCP3VZK7CMKC7J/action/replication_record"}},"created_at":"2026-07-05T11:07:23.733051+00:00","updated_at":"2026-07-05T11:07:23.733051+00:00"}