{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GAFMGVBPVHRG2HKVQ652I7HN7A","short_pith_number":"pith:GAFMGVBP","schema_version":"1.0","canonical_sha256":"300ac3542fa9e26d1d5587bba47cedf838ed6f0c274ba7aa36da23c1db0402f3","source":{"kind":"arxiv","id":"2406.04277","version":2},"attestation_state":"computed","paper":{"title":"VideoTetris: Towards Compositional Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Cui, Di Zhang, Haotian Yang, Jingmin Chen, Ling Yang, Pengfei Wan, Xin Tao, Xintao Wang, Ye Tian, Yuan Gao, Yufan Deng, Zhaochen Yu","submitted_at":"2024-06-06T17:25:33Z","abstract_excerpt":"Diffusion models have demonstrated great success in text-to-video (T2V) generation. However, existing methods may face challenges when handling complex (long) video generation scenarios that involve multiple objects or dynamic changes in object numbers. To address these limitations, we propose VideoTetris, a novel framework that enables compositional T2V generation. Specifically, we propose spatio-temporal compositional diffusion to precisely follow complex textual semantics by manipulating and composing the attention maps of denoising networks spatially and temporally. Moreover, we propose an"},"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":"2406.04277","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:25:33Z","cross_cats_sorted":[],"title_canon_sha256":"d9ec1a5c976aa72c5ec6ba890eb07a8478b1962bd32ed0c496da486c2ce5c508","abstract_canon_sha256":"fceae0e3d19f0d4965a234b5c6fb4597a155d78d838b250254289109d962519e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:58.339078Z","signature_b64":"CKYUiAd8JGhqEU7K5iNY5IkrMqqI3syLJu45uIm22Oiy1UqZp5U9s8CiSFsYg5Z65/pf7LQVYhrygWB2TyA2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"300ac3542fa9e26d1d5587bba47cedf838ed6f0c274ba7aa36da23c1db0402f3","last_reissued_at":"2026-07-05T09:19:58.338593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:58.338593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoTetris: Towards Compositional Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Cui, Di Zhang, Haotian Yang, Jingmin Chen, Ling Yang, Pengfei Wan, Xin Tao, Xintao Wang, Ye Tian, Yuan Gao, Yufan Deng, Zhaochen Yu","submitted_at":"2024-06-06T17:25:33Z","abstract_excerpt":"Diffusion models have demonstrated great success in text-to-video (T2V) generation. However, existing methods may face challenges when handling complex (long) video generation scenarios that involve multiple objects or dynamic changes in object numbers. To address these limitations, we propose VideoTetris, a novel framework that enables compositional T2V generation. Specifically, we propose spatio-temporal compositional diffusion to precisely follow complex textual semantics by manipulating and composing the attention maps of denoising networks spatially and temporally. Moreover, we propose an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04277","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/2406.04277/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":"2406.04277","created_at":"2026-07-05T09:19:58.338653+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04277v2","created_at":"2026-07-05T09:19:58.338653+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04277","created_at":"2026-07-05T09:19:58.338653+00:00"},{"alias_kind":"pith_short_12","alias_value":"GAFMGVBPVHRG","created_at":"2026-07-05T09:19:58.338653+00:00"},{"alias_kind":"pith_short_16","alias_value":"GAFMGVBPVHRG2HKV","created_at":"2026-07-05T09:19:58.338653+00:00"},{"alias_kind":"pith_short_8","alias_value":"GAFMGVBP","created_at":"2026-07-05T09:19:58.338653+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GAFMGVBPVHRG2HKVQ652I7HN7A","json":"https://pith.science/pith/GAFMGVBPVHRG2HKVQ652I7HN7A.json","graph_json":"https://pith.science/api/pith-number/GAFMGVBPVHRG2HKVQ652I7HN7A/graph.json","events_json":"https://pith.science/api/pith-number/GAFMGVBPVHRG2HKVQ652I7HN7A/events.json","paper":"https://pith.science/paper/GAFMGVBP"},"agent_actions":{"view_html":"https://pith.science/pith/GAFMGVBPVHRG2HKVQ652I7HN7A","download_json":"https://pith.science/pith/GAFMGVBPVHRG2HKVQ652I7HN7A.json","view_paper":"https://pith.science/paper/GAFMGVBP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04277&json=true","fetch_graph":"https://pith.science/api/pith-number/GAFMGVBPVHRG2HKVQ652I7HN7A/graph.json","fetch_events":"https://pith.science/api/pith-number/GAFMGVBPVHRG2HKVQ652I7HN7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GAFMGVBPVHRG2HKVQ652I7HN7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GAFMGVBPVHRG2HKVQ652I7HN7A/action/storage_attestation","attest_author":"https://pith.science/pith/GAFMGVBPVHRG2HKVQ652I7HN7A/action/author_attestation","sign_citation":"https://pith.science/pith/GAFMGVBPVHRG2HKVQ652I7HN7A/action/citation_signature","submit_replication":"https://pith.science/pith/GAFMGVBPVHRG2HKVQ652I7HN7A/action/replication_record"}},"created_at":"2026-07-05T09:19:58.338653+00:00","updated_at":"2026-07-05T09:19:58.338653+00:00"}