{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:43VBOPU6LJDGGZ3U2QA4O2RGIN","short_pith_number":"pith:43VBOPU6","schema_version":"1.0","canonical_sha256":"e6ea173e9e5a46636774d401c76a26434666cbea38bdfc95efc6a6c686dec741","source":{"kind":"arxiv","id":"2311.00990","version":2},"attestation_state":"computed","paper":{"title":"VideoDreamer: Customized Multi-Subject Text-to-Video Generation with Disen-Mix Finetuning on Language-Video Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feilin Han, Guanning Zeng, Hong Chen, Wenwu Zhu, Xin Wang, Yaofei Wu, Yipeng Zhang, Yuwei Zhou","submitted_at":"2023-11-02T04:38:50Z","abstract_excerpt":"Customized text-to-video generation aims to generate text-guided videos with user-given subjects, which has gained increasing attention. However, existing works are primarily limited to single-subject oriented text-to-video generation, leaving the more challenging problem of customized multi-subject generation unexplored. In this paper, we fill this gap and propose a novel VideoDreamer framework, which can generate temporally consistent text-guided videos that faithfully preserve the visual features of the given multiple subjects. Specifically, VideoDreamer adopts the pretrained Stable Diffusi"},"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":"2311.00990","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-02T04:38:50Z","cross_cats_sorted":[],"title_canon_sha256":"ca839d39e9ad93e32a2ef197d553d97847181e8e4528fe3b0ee4ef8afc0dc5bd","abstract_canon_sha256":"a3e0143e34de80629f7b472276073f1f0dbcb47fa64fb87b90606e5b52a71b7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:13.397909Z","signature_b64":"incJSZC/c86VK5oRyddZXL71u3ZBDMsxNfTzCt6AH8/8JNPPA64PUfa2diU3zk1nJZLocV8ZVO8OiEDmBMW7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6ea173e9e5a46636774d401c76a26434666cbea38bdfc95efc6a6c686dec741","last_reissued_at":"2026-07-05T10:48:13.397417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:13.397417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoDreamer: Customized Multi-Subject Text-to-Video Generation with Disen-Mix Finetuning on Language-Video Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feilin Han, Guanning Zeng, Hong Chen, Wenwu Zhu, Xin Wang, Yaofei Wu, Yipeng Zhang, Yuwei Zhou","submitted_at":"2023-11-02T04:38:50Z","abstract_excerpt":"Customized text-to-video generation aims to generate text-guided videos with user-given subjects, which has gained increasing attention. However, existing works are primarily limited to single-subject oriented text-to-video generation, leaving the more challenging problem of customized multi-subject generation unexplored. In this paper, we fill this gap and propose a novel VideoDreamer framework, which can generate temporally consistent text-guided videos that faithfully preserve the visual features of the given multiple subjects. Specifically, VideoDreamer adopts the pretrained Stable Diffusi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00990","kind":"arxiv","version":2},"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/2311.00990/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":"2311.00990","created_at":"2026-07-05T10:48:13.397470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00990v2","created_at":"2026-07-05T10:48:13.397470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00990","created_at":"2026-07-05T10:48:13.397470+00:00"},{"alias_kind":"pith_short_12","alias_value":"43VBOPU6LJDG","created_at":"2026-07-05T10:48:13.397470+00:00"},{"alias_kind":"pith_short_16","alias_value":"43VBOPU6LJDGGZ3U","created_at":"2026-07-05T10:48:13.397470+00:00"},{"alias_kind":"pith_short_8","alias_value":"43VBOPU6","created_at":"2026-07-05T10:48:13.397470+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":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/43VBOPU6LJDGGZ3U2QA4O2RGIN","json":"https://pith.science/pith/43VBOPU6LJDGGZ3U2QA4O2RGIN.json","graph_json":"https://pith.science/api/pith-number/43VBOPU6LJDGGZ3U2QA4O2RGIN/graph.json","events_json":"https://pith.science/api/pith-number/43VBOPU6LJDGGZ3U2QA4O2RGIN/events.json","paper":"https://pith.science/paper/43VBOPU6"},"agent_actions":{"view_html":"https://pith.science/pith/43VBOPU6LJDGGZ3U2QA4O2RGIN","download_json":"https://pith.science/pith/43VBOPU6LJDGGZ3U2QA4O2RGIN.json","view_paper":"https://pith.science/paper/43VBOPU6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00990&json=true","fetch_graph":"https://pith.science/api/pith-number/43VBOPU6LJDGGZ3U2QA4O2RGIN/graph.json","fetch_events":"https://pith.science/api/pith-number/43VBOPU6LJDGGZ3U2QA4O2RGIN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/43VBOPU6LJDGGZ3U2QA4O2RGIN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/43VBOPU6LJDGGZ3U2QA4O2RGIN/action/storage_attestation","attest_author":"https://pith.science/pith/43VBOPU6LJDGGZ3U2QA4O2RGIN/action/author_attestation","sign_citation":"https://pith.science/pith/43VBOPU6LJDGGZ3U2QA4O2RGIN/action/citation_signature","submit_replication":"https://pith.science/pith/43VBOPU6LJDGGZ3U2QA4O2RGIN/action/replication_record"}},"created_at":"2026-07-05T10:48:13.397470+00:00","updated_at":"2026-07-05T10:48:13.397470+00:00"}