{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KEHKVZJWT37TFCP3VZK7CMKC7J","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fc142ac0ef9799b1c157f16b9121e78f17e87dc2c17e74aa2ba2caa0eea35931","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-19T06:31:07Z","title_canon_sha256":"a3a7024154c1bbf8f9de2a609b1b45d3de6eb8d1489383bcbbd3ecca046c2d4e"},"schema_version":"1.0","source":{"id":"2504.14202","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14202","created_at":"2026-07-05T11:07:23Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14202v3","created_at":"2026-07-05T11:07:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14202","created_at":"2026-07-05T11:07:23Z"},{"alias_kind":"pith_short_12","alias_value":"KEHKVZJWT37T","created_at":"2026-07-05T11:07:23Z"},{"alias_kind":"pith_short_16","alias_value":"KEHKVZJWT37TFCP3","created_at":"2026-07-05T11:07:23Z"},{"alias_kind":"pith_short_8","alias_value":"KEHKVZJW","created_at":"2026-07-05T11:07:23Z"}],"graph_snapshots":[{"event_id":"sha256:85b69fc3823f3b6cc9edab048e3332647fd07d71712a9ca8f4e6839f53d36557","target":"graph","created_at":"2026-07-05T11:07:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.14202/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hao Kang, Liming Jiang, Qing Yan, Xin Lu, Yumin Jia, Zichuan Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-19T06:31:07Z","title":"Learning Joint ID-Textual Representation for ID-Preserving Image Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14202","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:71ab889d4c433274c31af1018831aa76a91718775ce3ee28b88d60c68b0c3766","target":"record","created_at":"2026-07-05T11:07:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fc142ac0ef9799b1c157f16b9121e78f17e87dc2c17e74aa2ba2caa0eea35931","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-19T06:31:07Z","title_canon_sha256":"a3a7024154c1bbf8f9de2a609b1b45d3de6eb8d1489383bcbbd3ecca046c2d4e"},"schema_version":"1.0","source":{"id":"2504.14202","kind":"arxiv","version":3}},"canonical_sha256":"510eaae5369eff3289fbae55f13142fa64ea90d8449d6431e48f9d48ae09e62b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"510eaae5369eff3289fbae55f13142fa64ea90d8449d6431e48f9d48ae09e62b","first_computed_at":"2026-07-05T11:07:23.732996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:23.732996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fBp8Ms8S2qDbtynF5Iiv5TtcaN3ngqyvv4e0qWTYjbAlmLawgvdVg0Nq7lsdt+YE/sN0pYP/dO6srJrS9Xd0Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:23.733493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14202","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71ab889d4c433274c31af1018831aa76a91718775ce3ee28b88d60c68b0c3766","sha256:85b69fc3823f3b6cc9edab048e3332647fd07d71712a9ca8f4e6839f53d36557"],"state_sha256":"45129ad2399ef22e76487c40a5ed7f70c98bc21ce89451c40b306c01e3500655"}