{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GUKR7RF3BTMGP2EYOUU7JHYZSH","short_pith_number":"pith:GUKR7RF3","schema_version":"1.0","canonical_sha256":"35151fc4bb0cd867e8987529f49f1991e0aabeee918cd813bde36b3bc304614e","source":{"kind":"arxiv","id":"2311.10709","version":2},"attestation_state":"computed","paper":{"title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Akbar Shah, Andrew Brown, Devi Parikh, Ishan Misra, Mannat Singh, Quentin Duval, Rohit Girdhar, Sai Saketh Rambhatla, Samaneh Azadi, Xi Yin","submitted_at":"2023-11-17T18:59:04Z","abstract_excerpt":"We present Emu Video, a text-to-video generation model that factorizes the generation into two steps: first generating an image conditioned on the text, and then generating a video conditioned on the text and the generated image. We identify critical design decisions--adjusted noise schedules for diffusion, and multi-stage training that enable us to directly generate high quality and high resolution videos, without requiring a deep cascade of models as in prior work. In human evaluations, our generated videos are strongly preferred in quality compared to all prior work--81% vs. Google's Imagen"},"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":"2311.10709","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-17T18:59:04Z","cross_cats_sorted":["cs.AI","cs.GR","cs.LG","cs.MM"],"title_canon_sha256":"f7a7e35bebde48b044b72ed3a96814dec40cf63ea18728dec770fa1dab7868ca","abstract_canon_sha256":"adeb1a4db5aa418c06b2f017b27c45d2ceeba2fe6567bf82547b88086d7ea5ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:44.761112Z","signature_b64":"2N6iNiZ7R2cioV1OrM2yvlO/UuG+pawAjMVOSZJe3EefpcprAfBYWpR/d5VuKDd7vtALbg/XpQBe+P2pXhKkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35151fc4bb0cd867e8987529f49f1991e0aabeee918cd813bde36b3bc304614e","last_reissued_at":"2026-07-05T08:51:44.760591Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:44.760591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Akbar Shah, Andrew Brown, Devi Parikh, Ishan Misra, Mannat Singh, Quentin Duval, Rohit Girdhar, Sai Saketh Rambhatla, Samaneh Azadi, Xi Yin","submitted_at":"2023-11-17T18:59:04Z","abstract_excerpt":"We present Emu Video, a text-to-video generation model that factorizes the generation into two steps: first generating an image conditioned on the text, and then generating a video conditioned on the text and the generated image. We identify critical design decisions--adjusted noise schedules for diffusion, and multi-stage training that enable us to directly generate high quality and high resolution videos, without requiring a deep cascade of models as in prior work. In human evaluations, our generated videos are strongly preferred in quality compared to all prior work--81% vs. Google's Imagen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10709","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/2311.10709/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":"2311.10709","created_at":"2026-07-05T08:51:44.760681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.10709v2","created_at":"2026-07-05T08:51:44.760681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10709","created_at":"2026-07-05T08:51:44.760681+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUKR7RF3BTMG","created_at":"2026-07-05T08:51:44.760681+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUKR7RF3BTMGP2EY","created_at":"2026-07-05T08:51:44.760681+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUKR7RF3","created_at":"2026-07-05T08:51:44.760681+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06361","citing_title":"Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2411.13549","citing_title":"KFC-W: Generating 3D-Consistent Videos from Unposed Internet Photos","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2412.03603","citing_title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2503.06310","citing_title":"Scene-Action Prompt Fusion for Coherent Text-to-Video Storytelling","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16819","citing_title":"Character-Centered Dialogue Generation from Scene-Level Prompts","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17248","citing_title":"Image-to-Video Diffusion: From Foundations to Open Frontiers","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2405.10314","citing_title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17019","citing_title":"StreamingEffect: Real-Time Human-Centric Video Effect Generation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24702","citing_title":"Enhancing Physical Plausibility in Video Generation by Reasoning the Implausibility","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2408.14837","citing_title":"Diffusion Models Are Real-Time Game Engines","ref_index":63,"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":20,"is_internal_anchor":false},{"citing_arxiv_id":"2404.12377","citing_title":"RoboDreamer: Learning Compositional World Models for Robot Imagination","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2409.16283","citing_title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14487","citing_title":"Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2503.00200","citing_title":"Unified Video Action Model","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2402.17177","citing_title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","ref_index":196,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06512","citing_title":"DCR: Counterfactual Attractor Guidance for Rare Compositional Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19741","citing_title":"CityRAG: Stepping Into a City via Spatially-Grounded Video Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GUKR7RF3BTMGP2EYOUU7JHYZSH","json":"https://pith.science/pith/GUKR7RF3BTMGP2EYOUU7JHYZSH.json","graph_json":"https://pith.science/api/pith-number/GUKR7RF3BTMGP2EYOUU7JHYZSH/graph.json","events_json":"https://pith.science/api/pith-number/GUKR7RF3BTMGP2EYOUU7JHYZSH/events.json","paper":"https://pith.science/paper/GUKR7RF3"},"agent_actions":{"view_html":"https://pith.science/pith/GUKR7RF3BTMGP2EYOUU7JHYZSH","download_json":"https://pith.science/pith/GUKR7RF3BTMGP2EYOUU7JHYZSH.json","view_paper":"https://pith.science/paper/GUKR7RF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.10709&json=true","fetch_graph":"https://pith.science/api/pith-number/GUKR7RF3BTMGP2EYOUU7JHYZSH/graph.json","fetch_events":"https://pith.science/api/pith-number/GUKR7RF3BTMGP2EYOUU7JHYZSH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUKR7RF3BTMGP2EYOUU7JHYZSH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUKR7RF3BTMGP2EYOUU7JHYZSH/action/storage_attestation","attest_author":"https://pith.science/pith/GUKR7RF3BTMGP2EYOUU7JHYZSH/action/author_attestation","sign_citation":"https://pith.science/pith/GUKR7RF3BTMGP2EYOUU7JHYZSH/action/citation_signature","submit_replication":"https://pith.science/pith/GUKR7RF3BTMGP2EYOUU7JHYZSH/action/replication_record"}},"created_at":"2026-07-05T08:51:44.760681+00:00","updated_at":"2026-07-05T08:51:44.760681+00:00"}