{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:N3HGIHHNZVXQMLQOVYUAUD3BUN","short_pith_number":"pith:N3HGIHHN","canonical_record":{"source":{"id":"2410.13720","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T16:22:46Z","cross_cats_sorted":["cs.AI","cs.LG","eess.IV"],"title_canon_sha256":"e60d521e9ef8d3ff3b782d17bc15c85e145010af217d90238c751ad180804d01","abstract_canon_sha256":"772b049fd7b20b900dbfdd735ce2c0878179fb58aec5b5c709246873cb7651a0"},"schema_version":"1.0"},"canonical_sha256":"6ece641cedcd6f062e0eae280a0f61a343827cfb69b52ee7683ce92796012b59","source":{"kind":"arxiv","id":"2410.13720","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13720","created_at":"2026-07-05T10:20:16Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13720v2","created_at":"2026-07-05T10:20:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13720","created_at":"2026-07-05T10:20:16Z"},{"alias_kind":"pith_short_12","alias_value":"N3HGIHHNZVXQ","created_at":"2026-07-05T10:20:16Z"},{"alias_kind":"pith_short_16","alias_value":"N3HGIHHNZVXQMLQO","created_at":"2026-07-05T10:20:16Z"},{"alias_kind":"pith_short_8","alias_value":"N3HGIHHN","created_at":"2026-07-05T10:20:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:N3HGIHHNZVXQMLQOVYUAUD3BUN","target":"record","payload":{"canonical_record":{"source":{"id":"2410.13720","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T16:22:46Z","cross_cats_sorted":["cs.AI","cs.LG","eess.IV"],"title_canon_sha256":"e60d521e9ef8d3ff3b782d17bc15c85e145010af217d90238c751ad180804d01","abstract_canon_sha256":"772b049fd7b20b900dbfdd735ce2c0878179fb58aec5b5c709246873cb7651a0"},"schema_version":"1.0"},"canonical_sha256":"6ece641cedcd6f062e0eae280a0f61a343827cfb69b52ee7683ce92796012b59","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:16.961908Z","signature_b64":"iKK9Eb0FV0vImIo83nUpuwqEq1N77hjL7Fo2pIwMh0QI4qpr6JTRWnXYtEQjtvz8E2aFWg6VYVrg6FANlt7rAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ece641cedcd6f062e0eae280a0f61a343827cfb69b52ee7683ce92796012b59","last_reissued_at":"2026-07-05T10:20:16.961365Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:16.961365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.13720","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:20:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3n6AmXkivZv0IaRHZimSL81fLDkZEfoNomzkh/rZ0qiqOUUo9NbEMdRUrsWmaIElizTYgg3/bM2GFFy9HYDYAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:23:09.867146Z"},"content_sha256":"032b83dcd9f270f828761c673e02f92b1b584b142e16c4970a5d63d3ed658644","schema_version":"1.0","event_id":"sha256:032b83dcd9f270f828761c673e02f92b1b584b142e16c4970a5d63d3ed658644"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:N3HGIHHNZVXQMLQOVYUAUD3BUN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Movie Gen: A Cast of Media Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Movie Gen introduces foundation models that generate 1080p videos with synchronized audio and claim state-of-the-art results on text-to-video, personalization, editing, and audio tasks.","cross_cats":["cs.AI","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Adam Polyak, Albert Pumarola, Ali Thabet, Amit Zohar, Andrew Brown, Andros Tjandra, Animesh Sinha, Ann Lee, Apoorv Vyas, Artsiom Sanakoyeu, Arun Mallya, Baishan Guo, Boris Araya, Bowen Shi, Breena Kerr, Carleigh Wood, Ce Liu, Cen Peng, Chih-Yao Ma, Ching-Yao Chuang, David Yan, Dhruv Choudhary, Dimitry Vengertsev, Dingkang Wang, Edgar Schonfeld, Elliot Blanchard, Felix Juefei-Xu, Fraylie Nord, Geet Sethi, Guan Pang, Haoyu Ma, Ishan Misra, Jeff Liang, Jialiang Wang, Ji Hou, John Hoffman, Jonas Kohler, Kaolin Fire, Karthik Sivakumar, Kiran Jagadeesh, Kunpeng Li, Lawrence Chen, Licheng Yu, Luxin Zhang, Luya Gao, Mannat Singh, Markos Georgopoulos, Mary Williamson, Matthew Yu, Matt Le, Mitesh Kumar Singh, Peizhao Zhang, Peter Vajda, Quentin Duval, Rashel Moritz, Rohit Girdhar, Roshan Sumbaly, Sai Saketh Rambhatla, Samaneh Azadi, Sam Tsai, Samyak Datta, Sanyuan Chen, Sara K. Sampson, Sean Bell, Sharadh Ramaswamy, Shelly Sheynin, Shikai Li, Siddharth Bhattacharya, Simone Parmeggiani, Simran Motwani, Steve Fine, Tao Xu, Tara Fowler, Tianhe Li, Tingbo Hou, Vladan Petrovic, Wei-Ning Hsu, Xiaoliang Dai, Xi Yin, Yaniv Taigman, Yaqiao Luo, Yen-Cheng Liu, Yi-Chiao Wu, Yue Zhao, Yuming Du, Yuval Kirstain, Zecheng He, Zijian He","submitted_at":"2024-10-17T16:22:46Z","abstract_excerpt":"We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user's image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation. Our largest video generation model is a 30B parameter transformer trained with a maximum context length of 73K video tokens, co"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The state-of-the-art claims rest on internal evaluations and comparisons whose details, baselines, and human preference protocols are not specified in the provided abstract.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A 30B-parameter transformer and related models generate high-quality videos and audio, claiming state-of-the-art results on text-to-video, video editing, personalization, and audio generation tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Movie Gen introduces foundation models that generate 1080p videos with synchronized audio and claim state-of-the-art results on text-to-video, personalization, editing, and audio tasks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6ad2237ff5f1c66dad2292f6861316d9ecb3d430047f9a523dea04646212c3aa"},"source":{"id":"2410.13720","kind":"arxiv","version":2},"verdict":{"id":"5566561b-1e7d-4771-828d-34000c29d1a7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T14:10:02.506352Z","strongest_claim":"Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation.","one_line_summary":"A 30B-parameter transformer and related models generate high-quality videos and audio, claiming state-of-the-art results on text-to-video, video editing, personalization, and audio generation tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The state-of-the-art claims rest on internal evaluations and comparisons whose details, baselines, and human preference protocols are not specified in the provided abstract.","pith_extraction_headline":"Movie Gen introduces foundation models that generate 1080p videos with synchronized audio and claim state-of-the-art results on text-to-video, personalization, editing, and audio tasks."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.13720/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":88,"sample":[{"doi":"","year":null,"title":"Latent- shift: Latent diffusion with temporal shift for efficient text-to-video generation","work_id":"bedd3bfc-5b36-4f28-80c6-ccc058c0b411","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","work_id":"2cd7b629-ab37-4ce5-b51e-aa4d99547468","ref_index":2,"cited_arxiv_id":"2211.01324","is_internal_anchor":true},{"doi":"","year":null,"title":"Lumiere: A space-time diffusion model for video generation","work_id":"8a0a0735-d82c-4090-a039-697d06ccc3f0","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"A Note on the Inception Score","work_id":"4700104e-68bd-4452-bdd6-e68281808831","ref_index":4,"cited_arxiv_id":"1801.01973","is_internal_anchor":false},{"doi":"","year":2022,"title":"Meta Open Compute Project, Grand Teton AI platform.https://engineering","work_id":"40d05d5e-9615-45c0-ab55-a2b9957326da","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":88,"snapshot_sha256":"f268a15cd1a217263e512de83bb46a803fd2829ec129ddd623a7fbb5bcc89f64","internal_anchors":35},"formal_canon":{"evidence_count":2,"snapshot_sha256":"da80f6339b3eb2f5dd844851c626da0cd79267f23173303556d95f54fa48d9c9"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"5566561b-1e7d-4771-828d-34000c29d1a7"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:20:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"25RQwPKh/cxhCi/7X40qEgzKCOAwAL3LhxlFDYhuMhlyFceDECAzcbnJLgIKwVhhYsh3+9DDhhE5bp+wKnjaAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:23:09.867962Z"},"content_sha256":"80719802c93cf0f24025b3a7e637483c972d836bfdbbb8a5ac485ae08ba46eb0","schema_version":"1.0","event_id":"sha256:80719802c93cf0f24025b3a7e637483c972d836bfdbbb8a5ac485ae08ba46eb0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N3HGIHHNZVXQMLQOVYUAUD3BUN/bundle.json","state_url":"https://pith.science/pith/N3HGIHHNZVXQMLQOVYUAUD3BUN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N3HGIHHNZVXQMLQOVYUAUD3BUN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T16:23:09Z","links":{"resolver":"https://pith.science/pith/N3HGIHHNZVXQMLQOVYUAUD3BUN","bundle":"https://pith.science/pith/N3HGIHHNZVXQMLQOVYUAUD3BUN/bundle.json","state":"https://pith.science/pith/N3HGIHHNZVXQMLQOVYUAUD3BUN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N3HGIHHNZVXQMLQOVYUAUD3BUN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N3HGIHHNZVXQMLQOVYUAUD3BUN","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":"772b049fd7b20b900dbfdd735ce2c0878179fb58aec5b5c709246873cb7651a0","cross_cats_sorted":["cs.AI","cs.LG","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T16:22:46Z","title_canon_sha256":"e60d521e9ef8d3ff3b782d17bc15c85e145010af217d90238c751ad180804d01"},"schema_version":"1.0","source":{"id":"2410.13720","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13720","created_at":"2026-07-05T10:20:16Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13720v2","created_at":"2026-07-05T10:20:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13720","created_at":"2026-07-05T10:20:16Z"},{"alias_kind":"pith_short_12","alias_value":"N3HGIHHNZVXQ","created_at":"2026-07-05T10:20:16Z"},{"alias_kind":"pith_short_16","alias_value":"N3HGIHHNZVXQMLQO","created_at":"2026-07-05T10:20:16Z"},{"alias_kind":"pith_short_8","alias_value":"N3HGIHHN","created_at":"2026-07-05T10:20:16Z"}],"graph_snapshots":[{"event_id":"sha256:80719802c93cf0f24025b3a7e637483c972d836bfdbbb8a5ac485ae08ba46eb0","target":"graph","created_at":"2026-07-05T10:20:16Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The state-of-the-art claims rest on internal evaluations and comparisons whose details, baselines, and human preference protocols are not specified in the provided abstract."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A 30B-parameter transformer and related models generate high-quality videos and audio, claiming state-of-the-art results on text-to-video, video editing, personalization, and audio generation tasks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Movie Gen introduces foundation models that generate 1080p videos with synchronized audio and claim state-of-the-art results on text-to-video, personalization, editing, and audio tasks."}],"snapshot_sha256":"6ad2237ff5f1c66dad2292f6861316d9ecb3d430047f9a523dea04646212c3aa"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"da80f6339b3eb2f5dd844851c626da0cd79267f23173303556d95f54fa48d9c9"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.13720/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user's image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation. Our largest video generation model is a 30B parameter transformer trained with a maximum context length of 73K video tokens, co","authors_text":"Adam Polyak, Albert Pumarola, Ali Thabet, Amit Zohar, Andrew Brown, Andros Tjandra, Animesh Sinha, Ann Lee, Apoorv Vyas, Artsiom Sanakoyeu, Arun Mallya, Baishan Guo, Boris Araya, Bowen Shi, Breena Kerr, Carleigh Wood, Ce Liu, Cen Peng, Chih-Yao Ma, Ching-Yao Chuang, David Yan, Dhruv Choudhary, Dimitry Vengertsev, Dingkang Wang, Edgar Schonfeld, Elliot Blanchard, Felix Juefei-Xu, Fraylie Nord, Geet Sethi, Guan Pang, Haoyu Ma, Ishan Misra, Jeff Liang, Jialiang Wang, Ji Hou, John Hoffman, Jonas Kohler, Kaolin Fire, Karthik Sivakumar, Kiran Jagadeesh, Kunpeng Li, Lawrence Chen, Licheng Yu, Luxin Zhang, Luya Gao, Mannat Singh, Markos Georgopoulos, Mary Williamson, Matthew Yu, Matt Le, Mitesh Kumar Singh, Peizhao Zhang, Peter Vajda, Quentin Duval, Rashel Moritz, Rohit Girdhar, Roshan Sumbaly, Sai Saketh Rambhatla, Samaneh Azadi, Sam Tsai, Samyak Datta, Sanyuan Chen, Sara K. Sampson, Sean Bell, Sharadh Ramaswamy, Shelly Sheynin, Shikai Li, Siddharth Bhattacharya, Simone Parmeggiani, Simran Motwani, Steve Fine, Tao Xu, Tara Fowler, Tianhe Li, Tingbo Hou, Vladan Petrovic, Wei-Ning Hsu, Xiaoliang Dai, Xi Yin, Yaniv Taigman, Yaqiao Luo, Yen-Cheng Liu, Yi-Chiao Wu, Yue Zhao, Yuming Du, Yuval Kirstain, Zecheng He, Zijian He","cross_cats":["cs.AI","cs.LG","eess.IV"],"headline":"Movie Gen introduces foundation models that generate 1080p videos with synchronized audio and claim state-of-the-art results on text-to-video, personalization, editing, and audio tasks.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T16:22:46Z","title":"Movie Gen: A Cast of Media Foundation Models"},"references":{"count":88,"internal_anchors":35,"resolved_work":88,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Latent- shift: Latent diffusion with temporal shift for efficient text-to-video generation","work_id":"bedd3bfc-5b36-4f28-80c6-ccc058c0b411","year":null},{"cited_arxiv_id":"2211.01324","doi":"","is_internal_anchor":true,"ref_index":2,"title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","work_id":"2cd7b629-ab37-4ce5-b51e-aa4d99547468","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Lumiere: A space-time diffusion model for video generation","work_id":"8a0a0735-d82c-4090-a039-697d06ccc3f0","year":null},{"cited_arxiv_id":"1801.01973","doi":"","is_internal_anchor":false,"ref_index":4,"title":"A Note on the Inception Score","work_id":"4700104e-68bd-4452-bdd6-e68281808831","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Meta Open Compute Project, Grand Teton AI platform.https://engineering","work_id":"40d05d5e-9615-45c0-ab55-a2b9957326da","year":2022}],"snapshot_sha256":"f268a15cd1a217263e512de83bb46a803fd2829ec129ddd623a7fbb5bcc89f64"},"source":{"id":"2410.13720","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-11T14:10:02.506352Z","id":"5566561b-1e7d-4771-828d-34000c29d1a7","model_set":{"reader":"grok-4.3"},"one_line_summary":"A 30B-parameter transformer and related models generate high-quality videos and audio, claiming state-of-the-art results on text-to-video, video editing, personalization, and audio generation tasks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Movie Gen introduces foundation models that generate 1080p videos with synchronized audio and claim state-of-the-art results on text-to-video, personalization, editing, and audio tasks.","strongest_claim":"Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation.","weakest_assumption":"The state-of-the-art claims rest on internal evaluations and comparisons whose details, baselines, and human preference protocols are not specified in the provided abstract."}},"verdict_id":"5566561b-1e7d-4771-828d-34000c29d1a7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:032b83dcd9f270f828761c673e02f92b1b584b142e16c4970a5d63d3ed658644","target":"record","created_at":"2026-07-05T10:20:16Z","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":"772b049fd7b20b900dbfdd735ce2c0878179fb58aec5b5c709246873cb7651a0","cross_cats_sorted":["cs.AI","cs.LG","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T16:22:46Z","title_canon_sha256":"e60d521e9ef8d3ff3b782d17bc15c85e145010af217d90238c751ad180804d01"},"schema_version":"1.0","source":{"id":"2410.13720","kind":"arxiv","version":2}},"canonical_sha256":"6ece641cedcd6f062e0eae280a0f61a343827cfb69b52ee7683ce92796012b59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ece641cedcd6f062e0eae280a0f61a343827cfb69b52ee7683ce92796012b59","first_computed_at":"2026-07-05T10:20:16.961365Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:20:16.961365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iKK9Eb0FV0vImIo83nUpuwqEq1N77hjL7Fo2pIwMh0QI4qpr6JTRWnXYtEQjtvz8E2aFWg6VYVrg6FANlt7rAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:20:16.961908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.13720","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:032b83dcd9f270f828761c673e02f92b1b584b142e16c4970a5d63d3ed658644","sha256:80719802c93cf0f24025b3a7e637483c972d836bfdbbb8a5ac485ae08ba46eb0"],"state_sha256":"b1d5dea4f41cbaba4667c7ae37aae3d5d836d2974206777c43485e043e01c6f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e1ntC+Vw2Xtrhtn7ODu2jK+JlWmtujKJ5aY73w1nsLx8UCa3d0Nm7d6mRmiu76+XAYDRXT0yQhoOInlDN6WOAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T16:23:09.874311Z","bundle_sha256":"3b6914723cec52a7c7dff6668f8acc248a4728233edca9dcb36599f8bb771180"}}