{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:S4O2PITO576APN5Q7CAPWDYMKL","short_pith_number":"pith:S4O2PITO","schema_version":"1.0","canonical_sha256":"971da7a26eeffc07b7b0f880fb0f0c52d9ea0407e04ac462c31bc5b7afbeb76a","source":{"kind":"arxiv","id":"2305.03374","version":4},"attestation_state":"computed","paper":{"title":"DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong Chen, Simin Wu, Wenwu Zhu, Xin Wang, Xuguang Duan, Yipeng Zhang, Yuwei Zhou","submitted_at":"2023-05-05T09:08:25Z","abstract_excerpt":"Subject-driven text-to-image generation aims to generate customized images of the given subject based on the text descriptions, which has drawn increasing attention. Existing methods mainly resort to finetuning a pretrained generative model, where the identity-relevant information (e.g., the boy) and the identity-irrelevant information (e.g., the background or the pose of the boy) are entangled in the latent embedding space. However, the highly entangled latent embedding may lead to the failure of subject-driven text-to-image generation as follows: (i) the identity-irrelevant information hidde"},"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":"2305.03374","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-05T09:08:25Z","cross_cats_sorted":[],"title_canon_sha256":"19efa4df2af50806525bac5781fd0828e89a623fb5821d32b482c12d68bfef20","abstract_canon_sha256":"985c3fac8f92cfe9f6e4102ba6af25f33081296c49e100a92803e50ea31be145"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:31.463490Z","signature_b64":"l00ruAbvrNNykPS7QSsBXyRp7ROPoXilK58dOO+1qevnPoTEB6dhy9OX7fGXYRlPp3gVmVv3y1p5L4BzeOVTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"971da7a26eeffc07b7b0f880fb0f0c52d9ea0407e04ac462c31bc5b7afbeb76a","last_reissued_at":"2026-07-05T07:49:31.463035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:31.463035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong Chen, Simin Wu, Wenwu Zhu, Xin Wang, Xuguang Duan, Yipeng Zhang, Yuwei Zhou","submitted_at":"2023-05-05T09:08:25Z","abstract_excerpt":"Subject-driven text-to-image generation aims to generate customized images of the given subject based on the text descriptions, which has drawn increasing attention. Existing methods mainly resort to finetuning a pretrained generative model, where the identity-relevant information (e.g., the boy) and the identity-irrelevant information (e.g., the background or the pose of the boy) are entangled in the latent embedding space. However, the highly entangled latent embedding may lead to the failure of subject-driven text-to-image generation as follows: (i) the identity-irrelevant information hidde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03374","kind":"arxiv","version":4},"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/2305.03374/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":"2305.03374","created_at":"2026-07-05T07:49:31.463104+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.03374v4","created_at":"2026-07-05T07:49:31.463104+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03374","created_at":"2026-07-05T07:49:31.463104+00:00"},{"alias_kind":"pith_short_12","alias_value":"S4O2PITO576A","created_at":"2026-07-05T07:49:31.463104+00:00"},{"alias_kind":"pith_short_16","alias_value":"S4O2PITO576APN5Q","created_at":"2026-07-05T07:49:31.463104+00:00"},{"alias_kind":"pith_short_8","alias_value":"S4O2PITO","created_at":"2026-07-05T07:49:31.463104+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22347","citing_title":"Customizing Video Portraits via Identity-ActionDecoupling","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22304","citing_title":"Encoder-Decoder Manifold Alignment for Idempotent Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19629","citing_title":"RIVET: Robust Idempotent Voice Attribute Editing","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2411.19182","citing_title":"SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2412.12242","citing_title":"OmniPrism: Learning Disentangled Visual Concept for Image Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2506.23690","citing_title":"SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07257","citing_title":"Adaptive Subspace Projection for Generative Personalization","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S4O2PITO576APN5Q7CAPWDYMKL","json":"https://pith.science/pith/S4O2PITO576APN5Q7CAPWDYMKL.json","graph_json":"https://pith.science/api/pith-number/S4O2PITO576APN5Q7CAPWDYMKL/graph.json","events_json":"https://pith.science/api/pith-number/S4O2PITO576APN5Q7CAPWDYMKL/events.json","paper":"https://pith.science/paper/S4O2PITO"},"agent_actions":{"view_html":"https://pith.science/pith/S4O2PITO576APN5Q7CAPWDYMKL","download_json":"https://pith.science/pith/S4O2PITO576APN5Q7CAPWDYMKL.json","view_paper":"https://pith.science/paper/S4O2PITO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.03374&json=true","fetch_graph":"https://pith.science/api/pith-number/S4O2PITO576APN5Q7CAPWDYMKL/graph.json","fetch_events":"https://pith.science/api/pith-number/S4O2PITO576APN5Q7CAPWDYMKL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S4O2PITO576APN5Q7CAPWDYMKL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S4O2PITO576APN5Q7CAPWDYMKL/action/storage_attestation","attest_author":"https://pith.science/pith/S4O2PITO576APN5Q7CAPWDYMKL/action/author_attestation","sign_citation":"https://pith.science/pith/S4O2PITO576APN5Q7CAPWDYMKL/action/citation_signature","submit_replication":"https://pith.science/pith/S4O2PITO576APN5Q7CAPWDYMKL/action/replication_record"}},"created_at":"2026-07-05T07:49:31.463104+00:00","updated_at":"2026-07-05T07:49:31.463104+00:00"}