{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LPUQJCZGIWK6M2HEPTTN6JA27Q","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":"77e56496d14af998776878e98e58e8e33f22bb22d63fb19f188f26841bf513f9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-21T15:59:07Z","title_canon_sha256":"99dc14d648899824de3bcc2f8e26bba57ce71854f795aee31ab15d910156e273"},"schema_version":"1.0","source":{"id":"2412.16677","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16677","created_at":"2026-07-05T09:53:11Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16677v1","created_at":"2026-07-05T09:53:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16677","created_at":"2026-07-05T09:53:11Z"},{"alias_kind":"pith_short_12","alias_value":"LPUQJCZGIWK6","created_at":"2026-07-05T09:53:11Z"},{"alias_kind":"pith_short_16","alias_value":"LPUQJCZGIWK6M2HE","created_at":"2026-07-05T09:53:11Z"},{"alias_kind":"pith_short_8","alias_value":"LPUQJCZG","created_at":"2026-07-05T09:53:11Z"}],"graph_snapshots":[{"event_id":"sha256:5336f994abbbe20adb5be336db90eb48cc81ec3567bfdb385a5c98d56ae50ab6","target":"graph","created_at":"2026-07-05T09:53:11Z","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/2412.16677/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating high-quality videos from textual descriptions poses challenges in maintaining temporal coherence and control over subject motion. We propose VAST (Video As Storyboard from Text), a two-stage framework to address these challenges and enable high-quality video generation. In the first stage, StoryForge transforms textual descriptions into detailed storyboards, capturing human poses and object layouts to represent the structural essence of the scene. In the second stage, VisionForge generates videos from these storyboards, producing high-quality videos with smooth motion, temporal cons","authors_text":"Chi Zhang, Fangqiu Yi, Xi Qiu, Xuelong Li, Yuanzhi Liang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-21T15:59:07Z","title":"VAST 1.0: A Unified Framework for Controllable and Consistent Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16677","kind":"arxiv","version":1},"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:a5b2d831cdf09aa088513bbdb93002f2f4bf5537b442b1ebcb27f33b2151edd6","target":"record","created_at":"2026-07-05T09:53:11Z","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":"77e56496d14af998776878e98e58e8e33f22bb22d63fb19f188f26841bf513f9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-21T15:59:07Z","title_canon_sha256":"99dc14d648899824de3bcc2f8e26bba57ce71854f795aee31ab15d910156e273"},"schema_version":"1.0","source":{"id":"2412.16677","kind":"arxiv","version":1}},"canonical_sha256":"5be9048b264595e668e47ce6df241afc25ca915ff69589bc6dad1f153a08566b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5be9048b264595e668e47ce6df241afc25ca915ff69589bc6dad1f153a08566b","first_computed_at":"2026-07-05T09:53:11.390133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:11.390133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"67kZMrhO4N/ghTtZPIQd2fPqNShfNqyi/Yp8eMbvyDODtWP4jeVooAczlYXpp9iK2/mzXgd/UQBwsNIgYGtCAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:11.390562Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16677","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5b2d831cdf09aa088513bbdb93002f2f4bf5537b442b1ebcb27f33b2151edd6","sha256:5336f994abbbe20adb5be336db90eb48cc81ec3567bfdb385a5c98d56ae50ab6"],"state_sha256":"7bd809d511db6ad73249aa07bc7f15c1011767c709da540a0361261376ea7427"}