{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M44AZR7KUISSMYFGAT2PSYYPBM","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":"230a2191ea85b2201b99bf2b8f086ab595e36b5159b23b660a63a7a64b90a4e2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T15:40:29Z","title_canon_sha256":"6674247ef4e27bb49c2ec829d0b8e94091ddb7195d8285ce828c482c1465f25f"},"schema_version":"1.0","source":{"id":"2407.02371","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02371","created_at":"2026-05-17T23:39:21Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02371v3","created_at":"2026-05-17T23:39:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02371","created_at":"2026-05-17T23:39:21Z"},{"alias_kind":"pith_short_12","alias_value":"M44AZR7KUISS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"M44AZR7KUISSMYFG","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"M44AZR7K","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:6231ae5a76e9f7a8e9d6540dae1d81b2661bf91ae5f37c3b578f14f2d72074f2","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":"we introduce OpenVid-1M, a precise high-quality dataset with expressive captions. This open-scenario dataset contains over 1 million text-video pairs, facilitating research on T2V generation. Furthermore, we curate 433K 1080p videos from OpenVid-1M to create OpenVidHD-0.4M... Additionally, we propose a novel Multi-modal Video Diffusion Transformer (MVDiT) capable of mining both structure information from visual tokens and semantic information from text tokens."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the newly collected videos and captions are verifiably higher quality and more precise than prior datasets such as WebVid-10M and Panda-70M, and that the MVDiT architecture delivers measurable gains attributable to its joint structure-semantic processing rather than other training factors."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"OpenVid-1M supplies 1 million high-quality text-video pairs and introduces MVDiT to improve text-to-video generation by better using both visual structure and text semantics."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"OpenVid-1M supplies over a million precise text-video pairs with expressive captions to improve text-to-video generation."}],"snapshot_sha256":"d1e5a278a927f2f0a14fb25bf3a2e912f56c98493e2af206dcb0108d0b413303"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8592a80c8d210d691955b92044057aa2dcc2f948421406dcfe90d9009d355ee8"},"paper":{"abstract_excerpt":"Text-to-video (T2V) generation has recently garnered significant attention thanks to the large multi-modality model Sora. However, T2V generation still faces two important challenges: 1) Lacking a precise open sourced high-quality dataset. The previous popular video datasets, e.g. WebVid-10M and Panda-70M, are either with low quality or too large for most research institutions. Therefore, it is challenging but crucial to collect a precise high-quality text-video pairs for T2V generation. 2) Ignoring to fully utilize textual information. Recent T2V methods have focused on vision transformers, u","authors_text":"Jian Yang, Kepan Nan, Penghao Zhou, Rui Xie, Tiehan Fan, Xiang Li, Ying Tai, Zhenheng Yang, Zhijie Chen","cross_cats":[],"headline":"OpenVid-1M supplies over a million precise text-video pairs with expressive captions to improve text-to-video generation.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T15:40:29Z","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation"},"references":{"count":16,"internal_anchors":7,"resolved_work":16,"sample":[{"cited_arxiv_id":"2311.15127","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","work_id":"4f68eada-27e3-437a-a2fe-6e4ca524d0d3","year":null},{"cited_arxiv_id":"2310.19512","doi":"","is_internal_anchor":true,"ref_index":2,"title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","work_id":"4d4486c5-6317-4d8d-bb5b-3b100d732a83","year":null},{"cited_arxiv_id":"1412.6980","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Adam: A Method for Stochastic Optimization","work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"arXiv preprint arXiv:2310.11440 (2023) 2, 4","work_id":"7e755299-7217-4af5-a711-0d29a31768fb","year":2024},{"cited_arxiv_id":"2401.03048","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Latte: Latent Diffusion Transformer for Video Generation","work_id":"5328e907-7278-4781-a2bb-c5ef40dc87fb","year":null}],"snapshot_sha256":"97813cc35b2ce4c32c795a3b2aba207cca435a803e2588e68f6a894280c6688f"},"source":{"id":"2407.02371","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-14T20:30:33.458442Z","id":"7a7d6e26-b04b-4512-b9c3-177d8561f47c","model_set":{"reader":"grok-4.3"},"one_line_summary":"OpenVid-1M supplies 1 million high-quality text-video pairs and introduces MVDiT to improve text-to-video generation by better using both visual structure and text semantics.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"OpenVid-1M supplies over a million precise text-video pairs with expressive captions to improve text-to-video generation.","strongest_claim":"we introduce OpenVid-1M, a precise high-quality dataset with expressive captions. This open-scenario dataset contains over 1 million text-video pairs, facilitating research on T2V generation. Furthermore, we curate 433K 1080p videos from OpenVid-1M to create OpenVidHD-0.4M... Additionally, we propose a novel Multi-modal Video Diffusion Transformer (MVDiT) capable of mining both structure information from visual tokens and semantic information from text tokens.","weakest_assumption":"That the newly collected videos and captions are verifiably higher quality and more precise than prior datasets such as WebVid-10M and Panda-70M, and that the MVDiT architecture delivers measurable gains attributable to its joint structure-semantic processing rather than other training factors."}},"verdict_id":"7a7d6e26-b04b-4512-b9c3-177d8561f47c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bfd8aa972583e132d1775a1a074359c38760e174ce5ab4b67bc42901a7d17785","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":"230a2191ea85b2201b99bf2b8f086ab595e36b5159b23b660a63a7a64b90a4e2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T15:40:29Z","title_canon_sha256":"6674247ef4e27bb49c2ec829d0b8e94091ddb7195d8285ce828c482c1465f25f"},"schema_version":"1.0","source":{"id":"2407.02371","kind":"arxiv","version":3}},"canonical_sha256":"67380cc7eaa2252660a604f4f9630f0b3c355564591318ef7194b0b8e63d550c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67380cc7eaa2252660a604f4f9630f0b3c355564591318ef7194b0b8e63d550c","first_computed_at":"2026-05-17T23:39:21.816981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:21.816981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CJgUeDV3hrFCFCcPD4TK2s84nlSjO0SHjDgwC3ocEP6MEztH/iDXRBhqAJsoi4Sk21+w1KWbXakcIUM/U2m3Bw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:21.817581Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.02371","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfd8aa972583e132d1775a1a074359c38760e174ce5ab4b67bc42901a7d17785","sha256:6231ae5a76e9f7a8e9d6540dae1d81b2661bf91ae5f37c3b578f14f2d72074f2"],"state_sha256":"f9ec9a67b08639b318d1b6a6c7b80a78907319683e7e619a976cc8e8e9b297ff"}