{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LGR2PPNSS2A5KIQOLT3BUTZHCD","short_pith_number":"pith:LGR2PPNS","schema_version":"1.0","canonical_sha256":"59a3a7bdb29681d5220e5cf61a4f2710cf3ac5cd0479896a84add047bf84be29","source":{"kind":"arxiv","id":"2502.05165","version":1},"attestation_state":"computed","paper":{"title":"Multitwine: Multi-Object Compositing with Text and Layout Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Gilbert, Gemma Canet Tarr\\'es, He Zhang, John Collomosse, Soo Ye Kim, Zhe Lin, Zhifei Zhang","submitted_at":"2025-02-07T18:48:54Z","abstract_excerpt":"We introduce the first generative model capable of simultaneous multi-object compositing, guided by both text and layout. Our model allows for the addition of multiple objects within a scene, capturing a range of interactions from simple positional relations (e.g., next to, in front of) to complex actions requiring reposing (e.g., hugging, playing guitar). When an interaction implies additional props, like `taking a selfie', our model autonomously generates these supporting objects. By jointly training for compositing and subject-driven generation, also known as customization, we achieve a mor"},"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":"2502.05165","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T18:48:54Z","cross_cats_sorted":[],"title_canon_sha256":"9c2559ca739043a70dea50a01d5444f1d4b82f589abbba3e183cbf96e1d97939","abstract_canon_sha256":"34489c69a10ae9d0b1d02047de5f4ed797ce9f8af4c8394a6c90cc9f4b25f170"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:10.290014Z","signature_b64":"lDwIP0TxxPKJ4ncyBVV/klXMQhhA0n90HWFivDaWyuT8yr/r9ZRrhhQxNNOS8sq2dLTsU+NqvNnrz4PFGA5tAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59a3a7bdb29681d5220e5cf61a4f2710cf3ac5cd0479896a84add047bf84be29","last_reissued_at":"2026-07-05T10:11:10.289517Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:10.289517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multitwine: Multi-Object Compositing with Text and Layout Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Gilbert, Gemma Canet Tarr\\'es, He Zhang, John Collomosse, Soo Ye Kim, Zhe Lin, Zhifei Zhang","submitted_at":"2025-02-07T18:48:54Z","abstract_excerpt":"We introduce the first generative model capable of simultaneous multi-object compositing, guided by both text and layout. Our model allows for the addition of multiple objects within a scene, capturing a range of interactions from simple positional relations (e.g., next to, in front of) to complex actions requiring reposing (e.g., hugging, playing guitar). When an interaction implies additional props, like `taking a selfie', our model autonomously generates these supporting objects. By jointly training for compositing and subject-driven generation, also known as customization, we achieve a mor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05165","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/2502.05165/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":"2502.05165","created_at":"2026-07-05T10:11:10.289582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05165v1","created_at":"2026-07-05T10:11:10.289582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05165","created_at":"2026-07-05T10:11:10.289582+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGR2PPNSS2A5","created_at":"2026-07-05T10:11:10.289582+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGR2PPNSS2A5KIQO","created_at":"2026-07-05T10:11:10.289582+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGR2PPNS","created_at":"2026-07-05T10:11:10.289582+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17450","citing_title":"BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LGR2PPNSS2A5KIQOLT3BUTZHCD","json":"https://pith.science/pith/LGR2PPNSS2A5KIQOLT3BUTZHCD.json","graph_json":"https://pith.science/api/pith-number/LGR2PPNSS2A5KIQOLT3BUTZHCD/graph.json","events_json":"https://pith.science/api/pith-number/LGR2PPNSS2A5KIQOLT3BUTZHCD/events.json","paper":"https://pith.science/paper/LGR2PPNS"},"agent_actions":{"view_html":"https://pith.science/pith/LGR2PPNSS2A5KIQOLT3BUTZHCD","download_json":"https://pith.science/pith/LGR2PPNSS2A5KIQOLT3BUTZHCD.json","view_paper":"https://pith.science/paper/LGR2PPNS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05165&json=true","fetch_graph":"https://pith.science/api/pith-number/LGR2PPNSS2A5KIQOLT3BUTZHCD/graph.json","fetch_events":"https://pith.science/api/pith-number/LGR2PPNSS2A5KIQOLT3BUTZHCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGR2PPNSS2A5KIQOLT3BUTZHCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGR2PPNSS2A5KIQOLT3BUTZHCD/action/storage_attestation","attest_author":"https://pith.science/pith/LGR2PPNSS2A5KIQOLT3BUTZHCD/action/author_attestation","sign_citation":"https://pith.science/pith/LGR2PPNSS2A5KIQOLT3BUTZHCD/action/citation_signature","submit_replication":"https://pith.science/pith/LGR2PPNSS2A5KIQOLT3BUTZHCD/action/replication_record"}},"created_at":"2026-07-05T10:11:10.289582+00:00","updated_at":"2026-07-05T10:11:10.289582+00:00"}