{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6WUX5DNT4R6GNCAQSAK5NEWA5S","short_pith_number":"pith:6WUX5DNT","schema_version":"1.0","canonical_sha256":"f5a97e8db3e47c6688109015d692c0ec99a1e3bde542f00ca52c6158d8ffda75","source":{"kind":"arxiv","id":"2405.12796","version":1},"attestation_state":"computed","paper":{"title":"DisenStudio: Customized Multi-subject Text-to-Video Generation with Disentangled Spatial Control","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong Chen, Siao Tang, Wenwu Zhu, Xin Wang, Yipeng Zhang, Yuwei Zhou, Zeyang Zhang","submitted_at":"2024-05-21T13:44:55Z","abstract_excerpt":"Generating customized content in videos has received increasing attention recently. However, existing works primarily focus on customized text-to-video generation for single subject, suffering from subject-missing and attribute-binding problems when the video is expected to contain multiple subjects. Furthermore, existing models struggle to assign the desired actions to the corresponding subjects (action-binding problem), failing to achieve satisfactory multi-subject generation performance. To tackle the problems, in this paper, we propose DisenStudio, a novel framework that can generate text-"},"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":"2405.12796","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-21T13:44:55Z","cross_cats_sorted":[],"title_canon_sha256":"ed4a57f69088531e994afb1b6fec103f06315b6fb2ec50813196e388fce7fcb3","abstract_canon_sha256":"e44fc7a3d0b28610350959b78810536f89fd3f465cf17bd87050f66fff7d84da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:26.064965Z","signature_b64":"JqpXi/0aPXJlGq0i+cuCx/FRZKJz0Y4l9ldWrqA10CqtK1FiwDFOGbaDuL2RfzLsuZwEsGBnTdllqkSQy08zCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5a97e8db3e47c6688109015d692c0ec99a1e3bde542f00ca52c6158d8ffda75","last_reissued_at":"2026-07-05T08:21:26.064437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:26.064437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DisenStudio: Customized Multi-subject Text-to-Video Generation with Disentangled Spatial Control","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong Chen, Siao Tang, Wenwu Zhu, Xin Wang, Yipeng Zhang, Yuwei Zhou, Zeyang Zhang","submitted_at":"2024-05-21T13:44:55Z","abstract_excerpt":"Generating customized content in videos has received increasing attention recently. However, existing works primarily focus on customized text-to-video generation for single subject, suffering from subject-missing and attribute-binding problems when the video is expected to contain multiple subjects. Furthermore, existing models struggle to assign the desired actions to the corresponding subjects (action-binding problem), failing to achieve satisfactory multi-subject generation performance. To tackle the problems, in this paper, we propose DisenStudio, a novel framework that can generate text-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12796","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/2405.12796/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":"2405.12796","created_at":"2026-07-05T08:21:26.064493+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.12796v1","created_at":"2026-07-05T08:21:26.064493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12796","created_at":"2026-07-05T08:21:26.064493+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WUX5DNT4R6G","created_at":"2026-07-05T08:21:26.064493+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WUX5DNT4R6GNCAQ","created_at":"2026-07-05T08:21:26.064493+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WUX5DNT","created_at":"2026-07-05T08:21:26.064493+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11244","citing_title":"Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Grounding","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6WUX5DNT4R6GNCAQSAK5NEWA5S","json":"https://pith.science/pith/6WUX5DNT4R6GNCAQSAK5NEWA5S.json","graph_json":"https://pith.science/api/pith-number/6WUX5DNT4R6GNCAQSAK5NEWA5S/graph.json","events_json":"https://pith.science/api/pith-number/6WUX5DNT4R6GNCAQSAK5NEWA5S/events.json","paper":"https://pith.science/paper/6WUX5DNT"},"agent_actions":{"view_html":"https://pith.science/pith/6WUX5DNT4R6GNCAQSAK5NEWA5S","download_json":"https://pith.science/pith/6WUX5DNT4R6GNCAQSAK5NEWA5S.json","view_paper":"https://pith.science/paper/6WUX5DNT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.12796&json=true","fetch_graph":"https://pith.science/api/pith-number/6WUX5DNT4R6GNCAQSAK5NEWA5S/graph.json","fetch_events":"https://pith.science/api/pith-number/6WUX5DNT4R6GNCAQSAK5NEWA5S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WUX5DNT4R6GNCAQSAK5NEWA5S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WUX5DNT4R6GNCAQSAK5NEWA5S/action/storage_attestation","attest_author":"https://pith.science/pith/6WUX5DNT4R6GNCAQSAK5NEWA5S/action/author_attestation","sign_citation":"https://pith.science/pith/6WUX5DNT4R6GNCAQSAK5NEWA5S/action/citation_signature","submit_replication":"https://pith.science/pith/6WUX5DNT4R6GNCAQSAK5NEWA5S/action/replication_record"}},"created_at":"2026-07-05T08:21:26.064493+00:00","updated_at":"2026-07-05T08:21:26.064493+00:00"}