{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3D5HRLFLJ2PGABDO2VUH76TONO","short_pith_number":"pith:3D5HRLFL","schema_version":"1.0","canonical_sha256":"d8fa78acab4e9e60046ed5687ffa6e6b90050d3f25f99e122ba93ed6d3107883","source":{"kind":"arxiv","id":"2403.16993","version":1},"attestation_state":"computed","paper":{"title":"Comp4D: LLM-Guided Compositional 4D Scene Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dejia Xu, Hanwen Liang, Hanxue Liang, Hezhen Hu, Konstantinos N. Plataniotis, Neel P. Bhatt, Zhangyang Wang","submitted_at":"2024-03-25T17:55:52Z","abstract_excerpt":"Recent advancements in diffusion models for 2D and 3D content creation have sparked a surge of interest in generating 4D content. However, the scarcity of 3D scene datasets constrains current methodologies to primarily object-centric generation. To overcome this limitation, we present Comp4D, a novel framework for Compositional 4D Generation. Unlike conventional methods that generate a singular 4D representation of the entire scene, Comp4D innovatively constructs each 4D object within the scene separately. Utilizing Large Language Models (LLMs), the framework begins by decomposing an input tex"},"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":"2403.16993","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:55:52Z","cross_cats_sorted":[],"title_canon_sha256":"038a5329d0870626c47cdffd8ab59c93442fdf12eab578c36de66f783617a94a","abstract_canon_sha256":"99da35f120ca1a598bdcb40d53abbacce1bf183ae1ad627ebf4a27d1b7a29e03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:23.484567Z","signature_b64":"YStSempXWNj70TOxw4N2MCKZOwPK0qEmmV+GFbZKg6nmqHmLlvWW/j7nLaBuKi0c35+bnPTYNfvPaOLbjExUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8fa78acab4e9e60046ed5687ffa6e6b90050d3f25f99e122ba93ed6d3107883","last_reissued_at":"2026-07-05T08:00:23.484097Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:23.484097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comp4D: LLM-Guided Compositional 4D Scene Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dejia Xu, Hanwen Liang, Hanxue Liang, Hezhen Hu, Konstantinos N. Plataniotis, Neel P. Bhatt, Zhangyang Wang","submitted_at":"2024-03-25T17:55:52Z","abstract_excerpt":"Recent advancements in diffusion models for 2D and 3D content creation have sparked a surge of interest in generating 4D content. However, the scarcity of 3D scene datasets constrains current methodologies to primarily object-centric generation. To overcome this limitation, we present Comp4D, a novel framework for Compositional 4D Generation. Unlike conventional methods that generate a singular 4D representation of the entire scene, Comp4D innovatively constructs each 4D object within the scene separately. Utilizing Large Language Models (LLMs), the framework begins by decomposing an input tex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16993","kind":"arxiv","version":1},"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/2403.16993/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":"2403.16993","created_at":"2026-07-05T08:00:23.484153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16993v1","created_at":"2026-07-05T08:00:23.484153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16993","created_at":"2026-07-05T08:00:23.484153+00:00"},{"alias_kind":"pith_short_12","alias_value":"3D5HRLFLJ2PG","created_at":"2026-07-05T08:00:23.484153+00:00"},{"alias_kind":"pith_short_16","alias_value":"3D5HRLFLJ2PGABDO","created_at":"2026-07-05T08:00:23.484153+00:00"},{"alias_kind":"pith_short_8","alias_value":"3D5HRLFL","created_at":"2026-07-05T08:00:23.484153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01766","citing_title":"SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09187","citing_title":"CP4D: Compositional Physics-aware 4D Scene Generation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2507.07982","citing_title":"Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2406.02509","citing_title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2601.00285","citing_title":"SV-GS: Sparse View 4D Reconstruction with Skeleton-Driven Gaussian Splatting","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3D5HRLFLJ2PGABDO2VUH76TONO","json":"https://pith.science/pith/3D5HRLFLJ2PGABDO2VUH76TONO.json","graph_json":"https://pith.science/api/pith-number/3D5HRLFLJ2PGABDO2VUH76TONO/graph.json","events_json":"https://pith.science/api/pith-number/3D5HRLFLJ2PGABDO2VUH76TONO/events.json","paper":"https://pith.science/paper/3D5HRLFL"},"agent_actions":{"view_html":"https://pith.science/pith/3D5HRLFLJ2PGABDO2VUH76TONO","download_json":"https://pith.science/pith/3D5HRLFLJ2PGABDO2VUH76TONO.json","view_paper":"https://pith.science/paper/3D5HRLFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16993&json=true","fetch_graph":"https://pith.science/api/pith-number/3D5HRLFLJ2PGABDO2VUH76TONO/graph.json","fetch_events":"https://pith.science/api/pith-number/3D5HRLFLJ2PGABDO2VUH76TONO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3D5HRLFLJ2PGABDO2VUH76TONO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3D5HRLFLJ2PGABDO2VUH76TONO/action/storage_attestation","attest_author":"https://pith.science/pith/3D5HRLFLJ2PGABDO2VUH76TONO/action/author_attestation","sign_citation":"https://pith.science/pith/3D5HRLFLJ2PGABDO2VUH76TONO/action/citation_signature","submit_replication":"https://pith.science/pith/3D5HRLFLJ2PGABDO2VUH76TONO/action/replication_record"}},"created_at":"2026-07-05T08:00:23.484153+00:00","updated_at":"2026-07-05T08:00:23.484153+00:00"}