{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:326CZJQ3BZ5YYZEXI547RHEH6P","short_pith_number":"pith:326CZJQ3","schema_version":"1.0","canonical_sha256":"debc2ca61b0e7b8c64974779f89c87f3c23f33d2ab7fbba42777ad3ff276fe10","source":{"kind":"arxiv","id":"2504.15009","version":1},"attestation_state":"computed","paper":{"title":"Insert Anything: Image Insertion via In-Context Editing in DiT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong Jiang, Ruijie Quan, Wensong Song, Yi Yang, Zongxing Yang","submitted_at":"2025-04-21T10:19:12Z","abstract_excerpt":"This work presents Insert Anything, a unified framework for reference-based image insertion that seamlessly integrates objects from reference images into target scenes under flexible, user-specified control guidance. Instead of training separate models for individual tasks, our approach is trained once on our new AnyInsertion dataset--comprising 120K prompt-image pairs covering diverse tasks such as person, object, and garment insertion--and effortlessly generalizes to a wide range of insertion scenarios. Such a challenging setting requires capturing both identity features and fine-grained det"},"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":"2504.15009","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T10:19:12Z","cross_cats_sorted":[],"title_canon_sha256":"73fef417ebaa68225ac91d8308178c7707b79e703ac38c954682be69c7d0381b","abstract_canon_sha256":"be91ac7de5b5542a131dd786aa8f85e221d6048975f944358929f3047874714e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:54.816954Z","signature_b64":"J2Yva5fdgkJohYtFZy3L/geKrQSXnuqqrlg9Yf4P79PaFJRwFwAM7OWNEJQqxH8qNHJ3V8VZpdK743nZDVodBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"debc2ca61b0e7b8c64974779f89c87f3c23f33d2ab7fbba42777ad3ff276fe10","last_reissued_at":"2026-07-05T10:51:54.816522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:54.816522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Insert Anything: Image Insertion via In-Context Editing in DiT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong Jiang, Ruijie Quan, Wensong Song, Yi Yang, Zongxing Yang","submitted_at":"2025-04-21T10:19:12Z","abstract_excerpt":"This work presents Insert Anything, a unified framework for reference-based image insertion that seamlessly integrates objects from reference images into target scenes under flexible, user-specified control guidance. Instead of training separate models for individual tasks, our approach is trained once on our new AnyInsertion dataset--comprising 120K prompt-image pairs covering diverse tasks such as person, object, and garment insertion--and effortlessly generalizes to a wide range of insertion scenarios. Such a challenging setting requires capturing both identity features and fine-grained det"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15009","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/2504.15009/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":"2504.15009","created_at":"2026-07-05T10:51:54.816583+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15009v1","created_at":"2026-07-05T10:51:54.816583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15009","created_at":"2026-07-05T10:51:54.816583+00:00"},{"alias_kind":"pith_short_12","alias_value":"326CZJQ3BZ5Y","created_at":"2026-07-05T10:51:54.816583+00:00"},{"alias_kind":"pith_short_16","alias_value":"326CZJQ3BZ5YYZEX","created_at":"2026-07-05T10:51:54.816583+00:00"},{"alias_kind":"pith_short_8","alias_value":"326CZJQ3","created_at":"2026-07-05T10:51:54.816583+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.17565","citing_title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01677","citing_title":"ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24894","citing_title":"BFS: Back-to-Front Layered Image Synthesis via Knowledge Transfer","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27773","citing_title":"ModaFlow: Modality-Aware Flow Matching for High-Fidelity Virtual Try-On","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2509.04434","citing_title":"Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2511.15197","citing_title":"Insert In Style: A Zero-Shot Generative Framework for Harmonious Cross-Domain Object Composition","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2603.02210","citing_title":"HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17565","citing_title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08836","citing_title":"CatalogStitch: Dimension-Aware and Occlusion-Preserving Object Compositing for Catalog Image Generation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16993","citing_title":"Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17565","citing_title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/326CZJQ3BZ5YYZEXI547RHEH6P","json":"https://pith.science/pith/326CZJQ3BZ5YYZEXI547RHEH6P.json","graph_json":"https://pith.science/api/pith-number/326CZJQ3BZ5YYZEXI547RHEH6P/graph.json","events_json":"https://pith.science/api/pith-number/326CZJQ3BZ5YYZEXI547RHEH6P/events.json","paper":"https://pith.science/paper/326CZJQ3"},"agent_actions":{"view_html":"https://pith.science/pith/326CZJQ3BZ5YYZEXI547RHEH6P","download_json":"https://pith.science/pith/326CZJQ3BZ5YYZEXI547RHEH6P.json","view_paper":"https://pith.science/paper/326CZJQ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15009&json=true","fetch_graph":"https://pith.science/api/pith-number/326CZJQ3BZ5YYZEXI547RHEH6P/graph.json","fetch_events":"https://pith.science/api/pith-number/326CZJQ3BZ5YYZEXI547RHEH6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/326CZJQ3BZ5YYZEXI547RHEH6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/326CZJQ3BZ5YYZEXI547RHEH6P/action/storage_attestation","attest_author":"https://pith.science/pith/326CZJQ3BZ5YYZEXI547RHEH6P/action/author_attestation","sign_citation":"https://pith.science/pith/326CZJQ3BZ5YYZEXI547RHEH6P/action/citation_signature","submit_replication":"https://pith.science/pith/326CZJQ3BZ5YYZEXI547RHEH6P/action/replication_record"}},"created_at":"2026-07-05T10:51:54.816583+00:00","updated_at":"2026-07-05T10:51:54.816583+00:00"}