{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CE6UHSSYIZOIZQSPP6JTFWKE4A","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":"2bca427249d4b40857a3991cb40c3ce214a50909dd8a5bd269297185d7728356","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-30T13:12:40Z","title_canon_sha256":"dbef2c651c70aba99234257294d313bd01fe92e9f497281450091b5eb06da62f"},"schema_version":"1.0","source":{"id":"2310.19512","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19512","created_at":"2026-05-17T23:39:21Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19512v1","created_at":"2026-05-17T23:39:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19512","created_at":"2026-05-17T23:39:21Z"},{"alias_kind":"pith_short_12","alias_value":"CE6UHSSYIZOI","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"CE6UHSSYIZOIZQSP","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"CE6UHSSY","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:baf037d4c7b0604769eaa4df1319ec6ebc07c6d10d19398435b5ec8025a47da8","target":"graph","created_at":"2026-05-17T23:39:21Z","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 proposed T2V model can generate realistic and cinematic-quality videos with a resolution of 1024 × 576, outperforming other open-source T2V models in terms of quality. The I2V model is the first open-source I2V foundation model capable of transforming a given image into a video clip while maintaining content preservation constraints."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the models achieve the stated quality, outperformance, and strict content preservation, which rests on unspecified training details, evaluation metrics, and comparisons not provided in the abstract."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Open-source text-to-video and image-to-video diffusion models generate high-quality 1024x576 videos, with the I2V variant claimed as the first to strictly preserve reference image content."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Open diffusion models generate realistic videos at 1024x576 resolution from text, with an image-to-video version that preserves input content."}],"snapshot_sha256":"26a43eb03499b864a0cf5d400d1688a7040ecd67c2e6b5b63740e5dd9c1e7cdf"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"48c27647a0639863ae022c6764e3894f10c0bbb17d182d8d29395c633332967b"},"paper":{"abstract_excerpt":"Video generation has increasingly gained interest in both academia and industry. Although commercial tools can generate plausible videos, there is a limited number of open-source models available for researchers and engineers. In this work, we introduce two diffusion models for high-quality video generation, namely text-to-video (T2V) and image-to-video (I2V) models. T2V models synthesize a video based on a given text input, while I2V models incorporate an additional image input. Our proposed T2V model can generate realistic and cinematic-quality videos with a resolution of $1024 \\times 576$, ","authors_text":"Chao Weng, Haoxin Chen, Jinbo Xing, Menghan Xia, Qifeng Chen, Shaoshu Yang, Xiaodong Cun, Xintao Wang, Yaofang Liu, Yingqing He, Ying Shan, Yong Zhang","cross_cats":[],"headline":"Open diffusion models generate realistic videos at 1024x576 resolution from text, with an image-to-video version that preserves input content.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-30T13:12:40Z","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation"},"references":{"count":63,"internal_anchors":14,"resolved_work":63,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Accessed October 22, 2023 [Online] https:// research.runwayml.com/gen2","work_id":"13424273-e098-4752-b508-3664d253c055","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Accessed October 22, 2023 [Online] https : / / github.com/deep-floyd/IF","work_id":"1f374479-4139-4a1a-9a9b-36e1914431f7","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Accessed October 22, 2023 [Online] https: //laion.ai/blog/laion-coco/","work_id":"77fb37fc-1c38-4984-ac70-290ea3a3b8c1","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Accessed October 22, 2023 [Online] https: //github.com/hotshotco/Hotshot-XL","work_id":"9a07b936-6609-4d38-8bd9-c271e4c8bba5","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Accessed October 22, 2023 [Online] https: //moonvalley.ai/","work_id":"23be4b42-07a0-452b-a925-35d30574fbd8","year":2023}],"snapshot_sha256":"4addebc6f30084e3d112e0c18f8750dba7b98813cb8eaecbd54a6dd2cbb31f4c"},"source":{"id":"2310.19512","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T21:36:24.597386Z","id":"233f9a2f-3823-47ad-929c-7ae7a25b849d","model_set":{"reader":"grok-4.3"},"one_line_summary":"Open-source text-to-video and image-to-video diffusion models generate high-quality 1024x576 videos, with the I2V variant claimed as the first to strictly preserve reference image content.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Open diffusion models generate realistic videos at 1024x576 resolution from text, with an image-to-video version that preserves input content.","strongest_claim":"Our proposed T2V model can generate realistic and cinematic-quality videos with a resolution of 1024 × 576, outperforming other open-source T2V models in terms of quality. The I2V model is the first open-source I2V foundation model capable of transforming a given image into a video clip while maintaining content preservation constraints.","weakest_assumption":"The assumption that the models achieve the stated quality, outperformance, and strict content preservation, which rests on unspecified training details, evaluation metrics, and comparisons not provided in the abstract."}},"verdict_id":"233f9a2f-3823-47ad-929c-7ae7a25b849d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6c69e73c9de0432a0e94d5d943446d7bef3db9c645815c794a1d6d4b4c6b87dd","target":"record","created_at":"2026-05-17T23:39:21Z","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":"2bca427249d4b40857a3991cb40c3ce214a50909dd8a5bd269297185d7728356","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-30T13:12:40Z","title_canon_sha256":"dbef2c651c70aba99234257294d313bd01fe92e9f497281450091b5eb06da62f"},"schema_version":"1.0","source":{"id":"2310.19512","kind":"arxiv","version":1}},"canonical_sha256":"113d43ca58465c8cc24f7f9332d944e00cd0458a20c85d8c0b7cfb37f6313405","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"113d43ca58465c8cc24f7f9332d944e00cd0458a20c85d8c0b7cfb37f6313405","first_computed_at":"2026-05-17T23:39:21.595918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:21.595918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7mSHpfztMaNTr4hAy5CuWIAUa+zd+NkhQpjPQ+xMsg0ZkdkbNjzAvusd/Z3Ij+uY4BayaPwMPO4ktojBOHwxBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:21.596609Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.19512","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c69e73c9de0432a0e94d5d943446d7bef3db9c645815c794a1d6d4b4c6b87dd","sha256:baf037d4c7b0604769eaa4df1319ec6ebc07c6d10d19398435b5ec8025a47da8"],"state_sha256":"a7d720199f6765ea817bb4d4ec55c2773fe9ec38cd2d9f68a7a6b8a2808bc369"}