{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C36KNOK3TPDUL7553FLNZCGWWI","short_pith_number":"pith:C36KNOK3","schema_version":"1.0","canonical_sha256":"16fca6b95b9bc745ffbdd956dc88d6b23ce7cb5dc0b96570ed9983923a94b3c9","source":{"kind":"arxiv","id":"2306.02018","version":2},"attestation_state":"computed","paper":{"title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dayou Chen, Deli Zhao, Hangjie Yuan, Jingren Zhou, Jiuniu Wang, Shiwei Zhang, Xiang Wang, Yingya Zhang, Yujun Shen","submitted_at":"2023-06-03T06:29:02Z","abstract_excerpt":"The pursuit of controllability as a higher standard of visual content creation has yielded remarkable progress in customizable image synthesis. However, achieving controllable video synthesis remains challenging due to the large variation of temporal dynamics and the requirement of cross-frame temporal consistency. Based on the paradigm of compositional generation, this work presents VideoComposer that allows users to flexibly compose a video with textual conditions, spatial conditions, and more importantly temporal conditions. Specifically, considering the characteristic of video data, we int"},"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":"2306.02018","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-03T06:29:02Z","cross_cats_sorted":[],"title_canon_sha256":"6e2c3f7c8692791cf595020caa017a3347c4bce3fbb6965b123c80c0158212c5","abstract_canon_sha256":"6628a653a015b97edebfe5ee12d22c6b8f6d988a07196fafdcedff244f48d72b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:53.002284Z","signature_b64":"IIum+YymQBlBp6DAMW/+zWMuNEXLYhjL3ElkBtrZuSq/HWCgUCf9orU+zqiWeskp/gn513ELTd2Z66cczk3rCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16fca6b95b9bc745ffbdd956dc88d6b23ce7cb5dc0b96570ed9983923a94b3c9","last_reissued_at":"2026-07-05T06:17:53.001726Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:53.001726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dayou Chen, Deli Zhao, Hangjie Yuan, Jingren Zhou, Jiuniu Wang, Shiwei Zhang, Xiang Wang, Yingya Zhang, Yujun Shen","submitted_at":"2023-06-03T06:29:02Z","abstract_excerpt":"The pursuit of controllability as a higher standard of visual content creation has yielded remarkable progress in customizable image synthesis. However, achieving controllable video synthesis remains challenging due to the large variation of temporal dynamics and the requirement of cross-frame temporal consistency. Based on the paradigm of compositional generation, this work presents VideoComposer that allows users to flexibly compose a video with textual conditions, spatial conditions, and more importantly temporal conditions. Specifically, considering the characteristic of video data, we int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02018","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/2306.02018/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":"2306.02018","created_at":"2026-07-05T06:17:53.001787+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.02018v2","created_at":"2026-07-05T06:17:53.001787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02018","created_at":"2026-07-05T06:17:53.001787+00:00"},{"alias_kind":"pith_short_12","alias_value":"C36KNOK3TPDU","created_at":"2026-07-05T06:17:53.001787+00:00"},{"alias_kind":"pith_short_16","alias_value":"C36KNOK3TPDUL755","created_at":"2026-07-05T06:17:53.001787+00:00"},{"alias_kind":"pith_short_8","alias_value":"C36KNOK3","created_at":"2026-07-05T06:17:53.001787+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25592","citing_title":"VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31109","citing_title":"InfiniVerse: Occupancy Guided Unbounded Scene Generation for Autonomous Driving","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30774","citing_title":"CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21431","citing_title":"iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2310.19512","citing_title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2308.06571","citing_title":"ModelScope Text-to-Video Technical Report","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C36KNOK3TPDUL7553FLNZCGWWI","json":"https://pith.science/pith/C36KNOK3TPDUL7553FLNZCGWWI.json","graph_json":"https://pith.science/api/pith-number/C36KNOK3TPDUL7553FLNZCGWWI/graph.json","events_json":"https://pith.science/api/pith-number/C36KNOK3TPDUL7553FLNZCGWWI/events.json","paper":"https://pith.science/paper/C36KNOK3"},"agent_actions":{"view_html":"https://pith.science/pith/C36KNOK3TPDUL7553FLNZCGWWI","download_json":"https://pith.science/pith/C36KNOK3TPDUL7553FLNZCGWWI.json","view_paper":"https://pith.science/paper/C36KNOK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.02018&json=true","fetch_graph":"https://pith.science/api/pith-number/C36KNOK3TPDUL7553FLNZCGWWI/graph.json","fetch_events":"https://pith.science/api/pith-number/C36KNOK3TPDUL7553FLNZCGWWI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C36KNOK3TPDUL7553FLNZCGWWI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C36KNOK3TPDUL7553FLNZCGWWI/action/storage_attestation","attest_author":"https://pith.science/pith/C36KNOK3TPDUL7553FLNZCGWWI/action/author_attestation","sign_citation":"https://pith.science/pith/C36KNOK3TPDUL7553FLNZCGWWI/action/citation_signature","submit_replication":"https://pith.science/pith/C36KNOK3TPDUL7553FLNZCGWWI/action/replication_record"}},"created_at":"2026-07-05T06:17:53.001787+00:00","updated_at":"2026-07-05T06:17:53.001787+00:00"}