{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6WUX5DNT4R6GNCAQSAK5NEWA5S","short_pith_number":"pith:6WUX5DNT","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"},"canonical_sha256":"f5a97e8db3e47c6688109015d692c0ec99a1e3bde542f00ca52c6158d8ffda75","source":{"kind":"arxiv","id":"2405.12796","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.12796","created_at":"2026-07-05T08:21:26Z"},{"alias_kind":"arxiv_version","alias_value":"2405.12796v1","created_at":"2026-07-05T08:21:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12796","created_at":"2026-07-05T08:21:26Z"},{"alias_kind":"pith_short_12","alias_value":"6WUX5DNT4R6G","created_at":"2026-07-05T08:21:26Z"},{"alias_kind":"pith_short_16","alias_value":"6WUX5DNT4R6GNCAQ","created_at":"2026-07-05T08:21:26Z"},{"alias_kind":"pith_short_8","alias_value":"6WUX5DNT","created_at":"2026-07-05T08:21:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6WUX5DNT4R6GNCAQSAK5NEWA5S","target":"record","payload":{"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"},"canonical_sha256":"f5a97e8db3e47c6688109015d692c0ec99a1e3bde542f00ca52c6158d8ffda75","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"},"source_kind":"arxiv","source_id":"2405.12796","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:21:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eOve3KvfDDXHVf6sJWbkTfBwkhEgQN2b1qy8Ykwglsa/ZdJfc0qknTaNxSIaSXBYBE2UdvuJOGKxreE+w3UjDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:21:01.090603Z"},"content_sha256":"601fcc375d40038366039017c284f34c0f70028082523175f2568edb17266ad0","schema_version":"1.0","event_id":"sha256:601fcc375d40038366039017c284f34c0f70028082523175f2568edb17266ad0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6WUX5DNT4R6GNCAQSAK5NEWA5S","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:21:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x2mRpwquct2dmZZRSuMi13snPvTo1bDEugdUqFZpBNAXa89hhxFZlDpXmct6iqZLKt75gdNPvjsLcdN7koNBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:21:01.091112Z"},"content_sha256":"407eb5ff14a0c416adda15af9c146da61b3d37066e5c3537990712687b470198","schema_version":"1.0","event_id":"sha256:407eb5ff14a0c416adda15af9c146da61b3d37066e5c3537990712687b470198"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6WUX5DNT4R6GNCAQSAK5NEWA5S/bundle.json","state_url":"https://pith.science/pith/6WUX5DNT4R6GNCAQSAK5NEWA5S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6WUX5DNT4R6GNCAQSAK5NEWA5S/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T07:21:01Z","links":{"resolver":"https://pith.science/pith/6WUX5DNT4R6GNCAQSAK5NEWA5S","bundle":"https://pith.science/pith/6WUX5DNT4R6GNCAQSAK5NEWA5S/bundle.json","state":"https://pith.science/pith/6WUX5DNT4R6GNCAQSAK5NEWA5S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6WUX5DNT4R6GNCAQSAK5NEWA5S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6WUX5DNT4R6GNCAQSAK5NEWA5S","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e44fc7a3d0b28610350959b78810536f89fd3f465cf17bd87050f66fff7d84da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-21T13:44:55Z","title_canon_sha256":"ed4a57f69088531e994afb1b6fec103f06315b6fb2ec50813196e388fce7fcb3"},"schema_version":"1.0","source":{"id":"2405.12796","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.12796","created_at":"2026-07-05T08:21:26Z"},{"alias_kind":"arxiv_version","alias_value":"2405.12796v1","created_at":"2026-07-05T08:21:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12796","created_at":"2026-07-05T08:21:26Z"},{"alias_kind":"pith_short_12","alias_value":"6WUX5DNT4R6G","created_at":"2026-07-05T08:21:26Z"},{"alias_kind":"pith_short_16","alias_value":"6WUX5DNT4R6GNCAQ","created_at":"2026-07-05T08:21:26Z"},{"alias_kind":"pith_short_8","alias_value":"6WUX5DNT","created_at":"2026-07-05T08:21:26Z"}],"graph_snapshots":[{"event_id":"sha256:407eb5ff14a0c416adda15af9c146da61b3d37066e5c3537990712687b470198","target":"graph","created_at":"2026-07-05T08:21:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.12796/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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-","authors_text":"Hong Chen, Siao Tang, Wenwu Zhu, Xin Wang, Yipeng Zhang, Yuwei Zhou, Zeyang Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-21T13:44:55Z","title":"DisenStudio: Customized Multi-subject Text-to-Video Generation with Disentangled Spatial Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12796","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:601fcc375d40038366039017c284f34c0f70028082523175f2568edb17266ad0","target":"record","created_at":"2026-07-05T08:21:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e44fc7a3d0b28610350959b78810536f89fd3f465cf17bd87050f66fff7d84da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-21T13:44:55Z","title_canon_sha256":"ed4a57f69088531e994afb1b6fec103f06315b6fb2ec50813196e388fce7fcb3"},"schema_version":"1.0","source":{"id":"2405.12796","kind":"arxiv","version":1}},"canonical_sha256":"f5a97e8db3e47c6688109015d692c0ec99a1e3bde542f00ca52c6158d8ffda75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5a97e8db3e47c6688109015d692c0ec99a1e3bde542f00ca52c6158d8ffda75","first_computed_at":"2026-07-05T08:21:26.064437Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:21:26.064437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JqpXi/0aPXJlGq0i+cuCx/FRZKJz0Y4l9ldWrqA10CqtK1FiwDFOGbaDuL2RfzLsuZwEsGBnTdllqkSQy08zCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:21:26.064965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.12796","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:601fcc375d40038366039017c284f34c0f70028082523175f2568edb17266ad0","sha256:407eb5ff14a0c416adda15af9c146da61b3d37066e5c3537990712687b470198"],"state_sha256":"d69a14dca6ec7a887c86b08f723ff99820f698cc87bcfcb201aa51c58758a18d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JJwfigMGTLxjEvqe6MpCQWf9fUXIC19URnRe8UbBm4lV3aS9k6CNlEu2L3V4z3TS6oTnks7TldLKXWUVK51ECQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T07:21:01.096043Z","bundle_sha256":"070743670b35d85232b17d35e278e98078fdb6d96b1a2787291570deb9b3ddf8"}}