{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PBOO7CBZ666CARC7NJV5C7I6HE","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":"20959ab8f45bf879e56ff3e8a3e1d7b64ad76c2664dcd601c54386b8b5a69e8a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T06:17:55Z","title_canon_sha256":"701d5945fb6cc252f8890063481960f2537a2ec232f99c1cd0002d4293d0cd96"},"schema_version":"1.0","source":{"id":"2406.06040","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06040","created_at":"2026-07-05T09:25:44Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06040v2","created_at":"2026-07-05T09:25:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06040","created_at":"2026-07-05T09:25:44Z"},{"alias_kind":"pith_short_12","alias_value":"PBOO7CBZ666C","created_at":"2026-07-05T09:25:44Z"},{"alias_kind":"pith_short_16","alias_value":"PBOO7CBZ666CARC7","created_at":"2026-07-05T09:25:44Z"},{"alias_kind":"pith_short_8","alias_value":"PBOO7CBZ","created_at":"2026-07-05T09:25:44Z"}],"graph_snapshots":[{"event_id":"sha256:2ccdbd88b5ebc608a148f970aba41c683ca028389e9c6b61d9793c06a15bc3e5","target":"graph","created_at":"2026-07-05T09:25:44Z","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/2406.06040/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chengqiang Lu, Dongjie Yang, Hai Zhao, Haoxin Zhang, Suyuan Huang, Xiaodong Han, Yan Gao, Yao Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T06:17:55Z","title":"Vript: A Video Is Worth Thousands of Words"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06040","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:f71eee7ec90d9f6e28a26113583ded4ce0e0aed1fa6adabddde2b3244d0c0a8b","target":"record","created_at":"2026-07-05T09:25:44Z","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":"20959ab8f45bf879e56ff3e8a3e1d7b64ad76c2664dcd601c54386b8b5a69e8a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T06:17:55Z","title_canon_sha256":"701d5945fb6cc252f8890063481960f2537a2ec232f99c1cd0002d4293d0cd96"},"schema_version":"1.0","source":{"id":"2406.06040","kind":"arxiv","version":2}},"canonical_sha256":"785cef8839f7bc20445f6a6bd17d1e3925722ee140bb511cf8e9bc638605d67a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"785cef8839f7bc20445f6a6bd17d1e3925722ee140bb511cf8e9bc638605d67a","first_computed_at":"2026-07-05T09:25:44.218228Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:44.218228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mYfVTMD5wBFeD4ML5+2zVlSnM5k+Sgv4/dLfkpL7IkRlR7asnTN6Nf3akSGnGP7M/XASpfwAlc1o4dSKfF9ICA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:44.218712Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06040","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f71eee7ec90d9f6e28a26113583ded4ce0e0aed1fa6adabddde2b3244d0c0a8b","sha256:2ccdbd88b5ebc608a148f970aba41c683ca028389e9c6b61d9793c06a15bc3e5"],"state_sha256":"3faff94f463f096d96405fba6269b0e9c829c523f5d98625715a5971c9b70043"}