{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3Y6ZXGPUGCHCLIBSKVTZAIVLFX","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":"f93ec68eeecc3e0838ed953081273441fdf8909a4a359002c98869c9e2099a77","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T17:54:46Z","title_canon_sha256":"4dff8381a5128d39c77dca619d553124f1fa121b10f8fe1c3b8aea3d08c4dac5"},"schema_version":"1.0","source":{"id":"2309.17444","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.17444","created_at":"2026-07-05T08:15:39Z"},{"alias_kind":"arxiv_version","alias_value":"2309.17444v3","created_at":"2026-07-05T08:15:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17444","created_at":"2026-07-05T08:15:39Z"},{"alias_kind":"pith_short_12","alias_value":"3Y6ZXGPUGCHC","created_at":"2026-07-05T08:15:39Z"},{"alias_kind":"pith_short_16","alias_value":"3Y6ZXGPUGCHCLIBS","created_at":"2026-07-05T08:15:39Z"},{"alias_kind":"pith_short_8","alias_value":"3Y6ZXGPU","created_at":"2026-07-05T08:15:39Z"}],"graph_snapshots":[{"event_id":"sha256:f19372e4a3158273a204d6963a29b9a1fbd3297e81605db87d2308b52d69d8dc","target":"graph","created_at":"2026-07-05T08:15:39Z","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/2309.17444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-conditioned diffusion models have emerged as a promising tool for neural video generation. However, current models still struggle with intricate spatiotemporal prompts and often generate restricted or incorrect motion. To address these limitations, we introduce LLM-grounded Video Diffusion (LVD). Instead of directly generating videos from the text inputs, LVD first leverages a large language model (LLM) to generate dynamic scene layouts based on the text inputs and subsequently uses the generated layouts to guide a diffusion model for video generation. We show that LLMs are able to unders","authors_text":"Adam Yala, Baifeng Shi, Boyi Li, Long Lian, Trevor Darrell","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T17:54:46Z","title":"LLM-grounded Video Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.17444","kind":"arxiv","version":3},"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:b9804cffd9aacf0d1765f7f896c36b5d96dcd32d135c24ed7c862db861d46d26","target":"record","created_at":"2026-07-05T08:15:39Z","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":"f93ec68eeecc3e0838ed953081273441fdf8909a4a359002c98869c9e2099a77","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T17:54:46Z","title_canon_sha256":"4dff8381a5128d39c77dca619d553124f1fa121b10f8fe1c3b8aea3d08c4dac5"},"schema_version":"1.0","source":{"id":"2309.17444","kind":"arxiv","version":3}},"canonical_sha256":"de3d9b99f4308e25a03255679022ab2de7071accd40de80d5868f4feafa0315e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de3d9b99f4308e25a03255679022ab2de7071accd40de80d5868f4feafa0315e","first_computed_at":"2026-07-05T08:15:39.817066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:15:39.817066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+2qIybtFHLghVUqYktppBWFnpU2DljTVSms4/KLHcYh4eFAMu+Ln+QC6SyyEJ4u0irH+d3AQ66zToSfG5WAlAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:15:39.817545Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.17444","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9804cffd9aacf0d1765f7f896c36b5d96dcd32d135c24ed7c862db861d46d26","sha256:f19372e4a3158273a204d6963a29b9a1fbd3297e81605db87d2308b52d69d8dc"],"state_sha256":"d104af9dd69611fcf3085a2f8a67afaff5ae42f2e9048153e6930ed529b100f2"}