{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AOVYRNIVUHRDDFK3K23VYOLRBF","short_pith_number":"pith:AOVYRNIV","schema_version":"1.0","canonical_sha256":"03ab88b515a1e231955b56b75c397109604473cbe41930068e7c473c7b36d77d","source":{"kind":"arxiv","id":"2403.14773","version":2},"attestation_state":"computed","paper":{"title":"StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM","eess.IV"],"primary_cat":"cs.CV","authors_text":"Daniil Hayrapetyan, Hayk Poghosyan, Humphrey Shi, Levon Khachatryan, Roberto Henschel, Shant Navasardyan, Vahram Tadevosyan, Zhangyang Wang","submitted_at":"2024-03-21T18:27:29Z","abstract_excerpt":"Text-to-video diffusion models enable the generation of high-quality videos that follow text instructions, making it easy to create diverse and individual content. However, existing approaches mostly focus on high-quality short video generation (typically 16 or 24 frames), ending up with hard-cuts when naively extended to the case of long video synthesis. To overcome these limitations, we introduce StreamingT2V, an autoregressive approach for long video generation of 80, 240, 600, 1200 or more frames with smooth transitions. The key components are:(i) a short-term memory block called condition"},"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":"2403.14773","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T18:27:29Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM","eess.IV"],"title_canon_sha256":"083c4cd11769040051835f09ed98a22d52dbcaa5f13d1baf7e9c61a8820a2c72","abstract_canon_sha256":"e3de63c7eabaa4296759d2c0fa2c6821824a60cdac2b8ab0c0f318d2298ab799"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:43.726234Z","signature_b64":"0uBfVrUw/fn6nkGeHPGFTO2I8CjZKoIZCwLBiooSTX0tOuLaUqQxjnmXb/fKL4LwnAfXYdrYQ6ZAsUIW2JZCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03ab88b515a1e231955b56b75c397109604473cbe41930068e7c473c7b36d77d","last_reissued_at":"2026-07-05T10:49:43.725745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:43.725745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM","eess.IV"],"primary_cat":"cs.CV","authors_text":"Daniil Hayrapetyan, Hayk Poghosyan, Humphrey Shi, Levon Khachatryan, Roberto Henschel, Shant Navasardyan, Vahram Tadevosyan, Zhangyang Wang","submitted_at":"2024-03-21T18:27:29Z","abstract_excerpt":"Text-to-video diffusion models enable the generation of high-quality videos that follow text instructions, making it easy to create diverse and individual content. However, existing approaches mostly focus on high-quality short video generation (typically 16 or 24 frames), ending up with hard-cuts when naively extended to the case of long video synthesis. To overcome these limitations, we introduce StreamingT2V, an autoregressive approach for long video generation of 80, 240, 600, 1200 or more frames with smooth transitions. The key components are:(i) a short-term memory block called condition"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14773","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/2403.14773/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":"2403.14773","created_at":"2026-07-05T10:49:43.725803+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.14773v2","created_at":"2026-07-05T10:49:43.725803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14773","created_at":"2026-07-05T10:49:43.725803+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOVYRNIVUHRD","created_at":"2026-07-05T10:49:43.725803+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOVYRNIVUHRDDFK3","created_at":"2026-07-05T10:49:43.725803+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOVYRNIV","created_at":"2026-07-05T10:49:43.725803+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09828","citing_title":"Latent Spatial Memory for Video World Models","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21472","citing_title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27677","citing_title":"DIM-WAM: World-Action Modeling with Diverse Historical Event Memory","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2503.06310","citing_title":"Scene-Action Prompt Fusion for Coherent Text-to-Video Storytelling","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16819","citing_title":"Character-Centered Dialogue Generation from Scene-Level Prompts","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21472","citing_title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17543","citing_title":"HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2505.21996","citing_title":"VRAG: Learning World Models for Interactive Video Generation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2508.09547","citing_title":"GoViG: Goal-Conditioned Visual Navigation Instruction Generation via Multimodal Reasoning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2602.02958","citing_title":"Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2602.07775","citing_title":"Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":211,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14487","citing_title":"Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06512","citing_title":"DCR: Counterfactual Attractor Guidance for Rare Compositional Generation","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AOVYRNIVUHRDDFK3K23VYOLRBF","json":"https://pith.science/pith/AOVYRNIVUHRDDFK3K23VYOLRBF.json","graph_json":"https://pith.science/api/pith-number/AOVYRNIVUHRDDFK3K23VYOLRBF/graph.json","events_json":"https://pith.science/api/pith-number/AOVYRNIVUHRDDFK3K23VYOLRBF/events.json","paper":"https://pith.science/paper/AOVYRNIV"},"agent_actions":{"view_html":"https://pith.science/pith/AOVYRNIVUHRDDFK3K23VYOLRBF","download_json":"https://pith.science/pith/AOVYRNIVUHRDDFK3K23VYOLRBF.json","view_paper":"https://pith.science/paper/AOVYRNIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.14773&json=true","fetch_graph":"https://pith.science/api/pith-number/AOVYRNIVUHRDDFK3K23VYOLRBF/graph.json","fetch_events":"https://pith.science/api/pith-number/AOVYRNIVUHRDDFK3K23VYOLRBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOVYRNIVUHRDDFK3K23VYOLRBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOVYRNIVUHRDDFK3K23VYOLRBF/action/storage_attestation","attest_author":"https://pith.science/pith/AOVYRNIVUHRDDFK3K23VYOLRBF/action/author_attestation","sign_citation":"https://pith.science/pith/AOVYRNIVUHRDDFK3K23VYOLRBF/action/citation_signature","submit_replication":"https://pith.science/pith/AOVYRNIVUHRDDFK3K23VYOLRBF/action/replication_record"}},"created_at":"2026-07-05T10:49:43.725803+00:00","updated_at":"2026-07-05T10:49:43.725803+00:00"}