{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3Y6ZXGPUGCHCLIBSKVTZAIVLFX","short_pith_number":"pith:3Y6ZXGPU","schema_version":"1.0","canonical_sha256":"de3d9b99f4308e25a03255679022ab2de7071accd40de80d5868f4feafa0315e","source":{"kind":"arxiv","id":"2309.17444","version":3},"attestation_state":"computed","paper":{"title":"LLM-grounded Video Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Adam Yala, Baifeng Shi, Boyi Li, Long Lian, Trevor Darrell","submitted_at":"2023-09-29T17:54:46Z","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"},"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":"2309.17444","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T17:54:46Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"4dff8381a5128d39c77dca619d553124f1fa121b10f8fe1c3b8aea3d08c4dac5","abstract_canon_sha256":"f93ec68eeecc3e0838ed953081273441fdf8909a4a359002c98869c9e2099a77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:39.817545Z","signature_b64":"+2qIybtFHLghVUqYktppBWFnpU2DljTVSms4/KLHcYh4eFAMu+Ln+QC6SyyEJ4u0irH+d3AQ66zToSfG5WAlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de3d9b99f4308e25a03255679022ab2de7071accd40de80d5868f4feafa0315e","last_reissued_at":"2026-07-05T08:15:39.817066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:39.817066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-grounded Video Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Adam Yala, Baifeng Shi, Boyi Li, Long Lian, Trevor Darrell","submitted_at":"2023-09-29T17:54:46Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.17444","kind":"arxiv","version":3},"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/2309.17444/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":"2309.17444","created_at":"2026-07-05T08:15:39.817124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.17444v3","created_at":"2026-07-05T08:15:39.817124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17444","created_at":"2026-07-05T08:15:39.817124+00:00"},{"alias_kind":"pith_short_12","alias_value":"3Y6ZXGPUGCHC","created_at":"2026-07-05T08:15:39.817124+00:00"},{"alias_kind":"pith_short_16","alias_value":"3Y6ZXGPUGCHCLIBS","created_at":"2026-07-05T08:15:39.817124+00:00"},{"alias_kind":"pith_short_8","alias_value":"3Y6ZXGPU","created_at":"2026-07-05T08:15:39.817124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24602","citing_title":"ViTexQA: A Multi-Frame Temporal Perception Dataset for Video Text Question Answering","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2405.07987","citing_title":"The Platonic Representation Hypothesis","ref_index":272,"is_internal_anchor":false},{"citing_arxiv_id":"2402.17177","citing_title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","ref_index":183,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11363","citing_title":"PresentAgent-2: Towards Generalist Multimodal Presentation Agents","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06512","citing_title":"DCR: Counterfactual Attractor Guidance for Rare Compositional Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07348","citing_title":"MoRight: Motion Control Done Right","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":100,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3Y6ZXGPUGCHCLIBSKVTZAIVLFX","json":"https://pith.science/pith/3Y6ZXGPUGCHCLIBSKVTZAIVLFX.json","graph_json":"https://pith.science/api/pith-number/3Y6ZXGPUGCHCLIBSKVTZAIVLFX/graph.json","events_json":"https://pith.science/api/pith-number/3Y6ZXGPUGCHCLIBSKVTZAIVLFX/events.json","paper":"https://pith.science/paper/3Y6ZXGPU"},"agent_actions":{"view_html":"https://pith.science/pith/3Y6ZXGPUGCHCLIBSKVTZAIVLFX","download_json":"https://pith.science/pith/3Y6ZXGPUGCHCLIBSKVTZAIVLFX.json","view_paper":"https://pith.science/paper/3Y6ZXGPU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.17444&json=true","fetch_graph":"https://pith.science/api/pith-number/3Y6ZXGPUGCHCLIBSKVTZAIVLFX/graph.json","fetch_events":"https://pith.science/api/pith-number/3Y6ZXGPUGCHCLIBSKVTZAIVLFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3Y6ZXGPUGCHCLIBSKVTZAIVLFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3Y6ZXGPUGCHCLIBSKVTZAIVLFX/action/storage_attestation","attest_author":"https://pith.science/pith/3Y6ZXGPUGCHCLIBSKVTZAIVLFX/action/author_attestation","sign_citation":"https://pith.science/pith/3Y6ZXGPUGCHCLIBSKVTZAIVLFX/action/citation_signature","submit_replication":"https://pith.science/pith/3Y6ZXGPUGCHCLIBSKVTZAIVLFX/action/replication_record"}},"created_at":"2026-07-05T08:15:39.817124+00:00","updated_at":"2026-07-05T08:15:39.817124+00:00"}