{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FEVL7PJX7VMA3UOO3INW37VHQF","short_pith_number":"pith:FEVL7PJX","schema_version":"1.0","canonical_sha256":"292abfbd37fd580dd1ceda1b6dfea781717181c142cc1d6dd6c5f1994aa40ff4","source":{"kind":"arxiv","id":"2406.14555","version":1},"attestation_state":"computed","paper":{"title":"A Survey of Multimodal-Guided Image Editing with Text-to-Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Henghui Ding, Rongcheng Tu, Xincheng Shuai, Xingjun Ma, Yu-Gang Jiang","submitted_at":"2024-06-20T17:58:52Z","abstract_excerpt":"Image editing aims to edit the given synthetic or real image to meet the specific requirements from users. It is widely studied in recent years as a promising and challenging field of Artificial Intelligence Generative Content (AIGC). Recent significant advancement in this field is based on the development of text-to-image (T2I) diffusion models, which generate images according to text prompts. These models demonstrate remarkable generative capabilities and have become widely used tools for image editing. T2I-based image editing methods significantly enhance editing performance and offer a use"},"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":"2406.14555","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-20T17:58:52Z","cross_cats_sorted":[],"title_canon_sha256":"9f456dbb5beef1a4eeabd0588b1647e41f4d17f49831d31f05e5456ff3377cc2","abstract_canon_sha256":"2d747f56592c632fb785d3096248434956362e0afd85686c345e224166325e80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:52.100291Z","signature_b64":"tbM/4nXBFXZkTbDSXjo0Hyj3NEAhshUyPfDDLF0OW4eTpIhbl/Wp5GliIjhhluZp+clDF/X9XV8WWccsYm9UBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"292abfbd37fd580dd1ceda1b6dfea781717181c142cc1d6dd6c5f1994aa40ff4","last_reissued_at":"2026-07-05T08:34:52.099798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:52.099798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Multimodal-Guided Image Editing with Text-to-Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Henghui Ding, Rongcheng Tu, Xincheng Shuai, Xingjun Ma, Yu-Gang Jiang","submitted_at":"2024-06-20T17:58:52Z","abstract_excerpt":"Image editing aims to edit the given synthetic or real image to meet the specific requirements from users. It is widely studied in recent years as a promising and challenging field of Artificial Intelligence Generative Content (AIGC). Recent significant advancement in this field is based on the development of text-to-image (T2I) diffusion models, which generate images according to text prompts. These models demonstrate remarkable generative capabilities and have become widely used tools for image editing. T2I-based image editing methods significantly enhance editing performance and offer a use"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14555","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/2406.14555/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":"2406.14555","created_at":"2026-07-05T08:34:52.099856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14555v1","created_at":"2026-07-05T08:34:52.099856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14555","created_at":"2026-07-05T08:34:52.099856+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEVL7PJX7VMA","created_at":"2026-07-05T08:34:52.099856+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEVL7PJX7VMA3UOO","created_at":"2026-07-05T08:34:52.099856+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEVL7PJX","created_at":"2026-07-05T08:34:52.099856+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02497","citing_title":"Seek to Segment: Active Perception for Panoramic Referring Segmentation","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25568","citing_title":"Rethinking Scribble-Guided Image Editing: Generalization, Instruction Adherence, and Multi-Tasking","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19750","citing_title":"CPC-VAR:Continual Personalized and Compositional Generation in Visual Autoregressive Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10204","citing_title":"3DReflecNet: A Large-Scale Dataset for 3D Reconstruction of Reflective, Transparent, and Low-Texture Objects","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26031","citing_title":"Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FEVL7PJX7VMA3UOO3INW37VHQF","json":"https://pith.science/pith/FEVL7PJX7VMA3UOO3INW37VHQF.json","graph_json":"https://pith.science/api/pith-number/FEVL7PJX7VMA3UOO3INW37VHQF/graph.json","events_json":"https://pith.science/api/pith-number/FEVL7PJX7VMA3UOO3INW37VHQF/events.json","paper":"https://pith.science/paper/FEVL7PJX"},"agent_actions":{"view_html":"https://pith.science/pith/FEVL7PJX7VMA3UOO3INW37VHQF","download_json":"https://pith.science/pith/FEVL7PJX7VMA3UOO3INW37VHQF.json","view_paper":"https://pith.science/paper/FEVL7PJX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14555&json=true","fetch_graph":"https://pith.science/api/pith-number/FEVL7PJX7VMA3UOO3INW37VHQF/graph.json","fetch_events":"https://pith.science/api/pith-number/FEVL7PJX7VMA3UOO3INW37VHQF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEVL7PJX7VMA3UOO3INW37VHQF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEVL7PJX7VMA3UOO3INW37VHQF/action/storage_attestation","attest_author":"https://pith.science/pith/FEVL7PJX7VMA3UOO3INW37VHQF/action/author_attestation","sign_citation":"https://pith.science/pith/FEVL7PJX7VMA3UOO3INW37VHQF/action/citation_signature","submit_replication":"https://pith.science/pith/FEVL7PJX7VMA3UOO3INW37VHQF/action/replication_record"}},"created_at":"2026-07-05T08:34:52.099856+00:00","updated_at":"2026-07-05T08:34:52.099856+00:00"}