{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GUKR7RF3BTMGP2EYOUU7JHYZSH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"adeb1a4db5aa418c06b2f017b27c45d2ceeba2fe6567bf82547b88086d7ea5ec","cross_cats_sorted":["cs.AI","cs.GR","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-17T18:59:04Z","title_canon_sha256":"f7a7e35bebde48b044b72ed3a96814dec40cf63ea18728dec770fa1dab7868ca"},"schema_version":"1.0","source":{"id":"2311.10709","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.10709","created_at":"2026-07-05T08:51:44Z"},{"alias_kind":"arxiv_version","alias_value":"2311.10709v2","created_at":"2026-07-05T08:51:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10709","created_at":"2026-07-05T08:51:44Z"},{"alias_kind":"pith_short_12","alias_value":"GUKR7RF3BTMG","created_at":"2026-07-05T08:51:44Z"},{"alias_kind":"pith_short_16","alias_value":"GUKR7RF3BTMGP2EY","created_at":"2026-07-05T08:51:44Z"},{"alias_kind":"pith_short_8","alias_value":"GUKR7RF3","created_at":"2026-07-05T08:51:44Z"}],"graph_snapshots":[{"event_id":"sha256:5fe427dd5e12e5c8c427a59bb0773fcbf4bab7a732dd19c416b116f5c7fe826e","target":"graph","created_at":"2026-07-05T08:51:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.10709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Akbar Shah, Andrew Brown, Devi Parikh, Ishan Misra, Mannat Singh, Quentin Duval, Rohit Girdhar, Sai Saketh Rambhatla, Samaneh Azadi, Xi Yin","cross_cats":["cs.AI","cs.GR","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-17T18:59:04Z","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10709","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:aa3c16ec6d5221e81ba4d894f6574c890534b189b0915725dec9c519d0d47d5b","target":"record","created_at":"2026-07-05T08:51:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"adeb1a4db5aa418c06b2f017b27c45d2ceeba2fe6567bf82547b88086d7ea5ec","cross_cats_sorted":["cs.AI","cs.GR","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-17T18:59:04Z","title_canon_sha256":"f7a7e35bebde48b044b72ed3a96814dec40cf63ea18728dec770fa1dab7868ca"},"schema_version":"1.0","source":{"id":"2311.10709","kind":"arxiv","version":2}},"canonical_sha256":"35151fc4bb0cd867e8987529f49f1991e0aabeee918cd813bde36b3bc304614e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35151fc4bb0cd867e8987529f49f1991e0aabeee918cd813bde36b3bc304614e","first_computed_at":"2026-07-05T08:51:44.760591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:51:44.760591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2N6iNiZ7R2cioV1OrM2yvlO/UuG+pawAjMVOSZJe3EefpcprAfBYWpR/d5VuKDd7vtALbg/XpQBe+P2pXhKkDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:51:44.761112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.10709","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa3c16ec6d5221e81ba4d894f6574c890534b189b0915725dec9c519d0d47d5b","sha256:5fe427dd5e12e5c8c427a59bb0773fcbf4bab7a732dd19c416b116f5c7fe826e"],"state_sha256":"25b9083d99947e3d6406d792b4518e3459a85d46b86ebd860eef213cd6517174"}