{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PBOO7CBZ666CARC7NJV5C7I6HE","short_pith_number":"pith:PBOO7CBZ","schema_version":"1.0","canonical_sha256":"785cef8839f7bc20445f6a6bd17d1e3925722ee140bb511cf8e9bc638605d67a","source":{"kind":"arxiv","id":"2406.06040","version":2},"attestation_state":"computed","paper":{"title":"Vript: A Video Is Worth Thousands of Words","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengqiang Lu, Dongjie Yang, Hai Zhao, Haoxin Zhang, Suyuan Huang, Xiaodong Han, Yan Gao, Yao Hu","submitted_at":"2024-06-10T06:17:55Z","abstract_excerpt":"Advancements in multimodal learning, particularly in video understanding and generation, require high-quality video-text datasets for improved model performance. Vript addresses this issue with a meticulously annotated corpus of 12K high-resolution videos, offering detailed, dense, and script-like captions for over 420K clips. Each clip has a caption of ~145 words, which is over 10x longer than most video-text datasets. Unlike captions only documenting static content in previous datasets, we enhance video captioning to video scripting by documenting not just the content, but also the camera op"},"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":"2406.06040","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T06:17:55Z","cross_cats_sorted":[],"title_canon_sha256":"701d5945fb6cc252f8890063481960f2537a2ec232f99c1cd0002d4293d0cd96","abstract_canon_sha256":"20959ab8f45bf879e56ff3e8a3e1d7b64ad76c2664dcd601c54386b8b5a69e8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:44.218712Z","signature_b64":"mYfVTMD5wBFeD4ML5+2zVlSnM5k+Sgv4/dLfkpL7IkRlR7asnTN6Nf3akSGnGP7M/XASpfwAlc1o4dSKfF9ICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"785cef8839f7bc20445f6a6bd17d1e3925722ee140bb511cf8e9bc638605d67a","last_reissued_at":"2026-07-05T09:25:44.218228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:44.218228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vript: A Video Is Worth Thousands of Words","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengqiang Lu, Dongjie Yang, Hai Zhao, Haoxin Zhang, Suyuan Huang, Xiaodong Han, Yan Gao, Yao Hu","submitted_at":"2024-06-10T06:17:55Z","abstract_excerpt":"Advancements in multimodal learning, particularly in video understanding and generation, require high-quality video-text datasets for improved model performance. Vript addresses this issue with a meticulously annotated corpus of 12K high-resolution videos, offering detailed, dense, and script-like captions for over 420K clips. Each clip has a caption of ~145 words, which is over 10x longer than most video-text datasets. Unlike captions only documenting static content in previous datasets, we enhance video captioning to video scripting by documenting not just the content, but also the camera op"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06040","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/2406.06040/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":"2406.06040","created_at":"2026-07-05T09:25:44.218282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06040v2","created_at":"2026-07-05T09:25:44.218282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06040","created_at":"2026-07-05T09:25:44.218282+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBOO7CBZ666C","created_at":"2026-07-05T09:25:44.218282+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBOO7CBZ666CARC7","created_at":"2026-07-05T09:25:44.218282+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBOO7CBZ","created_at":"2026-07-05T09:25:44.218282+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.00574","citing_title":"VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2501.12386","citing_title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2504.05299","citing_title":"SmolVLM: Redefining small and efficient multimodal models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2412.20404","citing_title":"Open-Sora: Democratizing Efficient Video Production for All","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":270,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PBOO7CBZ666CARC7NJV5C7I6HE","json":"https://pith.science/pith/PBOO7CBZ666CARC7NJV5C7I6HE.json","graph_json":"https://pith.science/api/pith-number/PBOO7CBZ666CARC7NJV5C7I6HE/graph.json","events_json":"https://pith.science/api/pith-number/PBOO7CBZ666CARC7NJV5C7I6HE/events.json","paper":"https://pith.science/paper/PBOO7CBZ"},"agent_actions":{"view_html":"https://pith.science/pith/PBOO7CBZ666CARC7NJV5C7I6HE","download_json":"https://pith.science/pith/PBOO7CBZ666CARC7NJV5C7I6HE.json","view_paper":"https://pith.science/paper/PBOO7CBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06040&json=true","fetch_graph":"https://pith.science/api/pith-number/PBOO7CBZ666CARC7NJV5C7I6HE/graph.json","fetch_events":"https://pith.science/api/pith-number/PBOO7CBZ666CARC7NJV5C7I6HE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBOO7CBZ666CARC7NJV5C7I6HE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBOO7CBZ666CARC7NJV5C7I6HE/action/storage_attestation","attest_author":"https://pith.science/pith/PBOO7CBZ666CARC7NJV5C7I6HE/action/author_attestation","sign_citation":"https://pith.science/pith/PBOO7CBZ666CARC7NJV5C7I6HE/action/citation_signature","submit_replication":"https://pith.science/pith/PBOO7CBZ666CARC7NJV5C7I6HE/action/replication_record"}},"created_at":"2026-07-05T09:25:44.218282+00:00","updated_at":"2026-07-05T09:25:44.218282+00:00"}