{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KVOQZRWN5OSVLRUTVBFIJMWUF7","short_pith_number":"pith:KVOQZRWN","schema_version":"1.0","canonical_sha256":"555d0cc6cdeba555c693a84a84b2d42fd81dec922fd70e4c824da6904a9c8cb7","source":{"kind":"arxiv","id":"2312.13763","version":2},"attestation_state":"computed","paper":{"title":"Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Huan Ling, Karsten Kreis, Sanja Fidler, Seung Wook Kim","submitted_at":"2023-12-21T11:41:02Z","abstract_excerpt":"Text-guided diffusion models have revolutionized image and video generation and have also been successfully used for optimization-based 3D object synthesis. Here, we instead focus on the underexplored text-to-4D setting and synthesize dynamic, animated 3D objects using score distillation methods with an additional temporal dimension. Compared to previous work, we pursue a novel compositional generation-based approach, and combine text-to-image, text-to-video, and 3D-aware multiview diffusion models to provide feedback during 4D object optimization, thereby simultaneously enforcing temporal con"},"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":"2312.13763","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T11:41:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"47219bae6daec216b69a09af1cc935fdcd3e02a672970bc1b2ab9197aa32dc67","abstract_canon_sha256":"8fe14639ccd34be0decba2ce6642a67a71af476193310c5ad8ce0545b8a11b87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:40.870594Z","signature_b64":"9PTK0l4tXlSPPpOWdck8tpJ+bC+bGFBg/aqwZY41fxH+tAyQakxL+jI6wmCRuEX8W9DgCPEnbe5iSoj9xnpBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"555d0cc6cdeba555c693a84a84b2d42fd81dec922fd70e4c824da6904a9c8cb7","last_reissued_at":"2026-07-05T07:29:40.870123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:40.870123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Huan Ling, Karsten Kreis, Sanja Fidler, Seung Wook Kim","submitted_at":"2023-12-21T11:41:02Z","abstract_excerpt":"Text-guided diffusion models have revolutionized image and video generation and have also been successfully used for optimization-based 3D object synthesis. Here, we instead focus on the underexplored text-to-4D setting and synthesize dynamic, animated 3D objects using score distillation methods with an additional temporal dimension. Compared to previous work, we pursue a novel compositional generation-based approach, and combine text-to-image, text-to-video, and 3D-aware multiview diffusion models to provide feedback during 4D object optimization, thereby simultaneously enforcing temporal con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13763","kind":"arxiv","version":2},"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/2312.13763/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":"2312.13763","created_at":"2026-07-05T07:29:40.870174+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.13763v2","created_at":"2026-07-05T07:29:40.870174+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13763","created_at":"2026-07-05T07:29:40.870174+00:00"},{"alias_kind":"pith_short_12","alias_value":"KVOQZRWN5OSV","created_at":"2026-07-05T07:29:40.870174+00:00"},{"alias_kind":"pith_short_16","alias_value":"KVOQZRWN5OSVLRUT","created_at":"2026-07-05T07:29:40.870174+00:00"},{"alias_kind":"pith_short_8","alias_value":"KVOQZRWN","created_at":"2026-07-05T07:29:40.870174+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22131","citing_title":"Feed-forward Motion In-betweening for Any 4D","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26917","citing_title":"AnimateAnyMesh++: A Flexible 4D Foundation Model for High-Fidelity Text-Driven Mesh Animation","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KVOQZRWN5OSVLRUTVBFIJMWUF7","json":"https://pith.science/pith/KVOQZRWN5OSVLRUTVBFIJMWUF7.json","graph_json":"https://pith.science/api/pith-number/KVOQZRWN5OSVLRUTVBFIJMWUF7/graph.json","events_json":"https://pith.science/api/pith-number/KVOQZRWN5OSVLRUTVBFIJMWUF7/events.json","paper":"https://pith.science/paper/KVOQZRWN"},"agent_actions":{"view_html":"https://pith.science/pith/KVOQZRWN5OSVLRUTVBFIJMWUF7","download_json":"https://pith.science/pith/KVOQZRWN5OSVLRUTVBFIJMWUF7.json","view_paper":"https://pith.science/paper/KVOQZRWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.13763&json=true","fetch_graph":"https://pith.science/api/pith-number/KVOQZRWN5OSVLRUTVBFIJMWUF7/graph.json","fetch_events":"https://pith.science/api/pith-number/KVOQZRWN5OSVLRUTVBFIJMWUF7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KVOQZRWN5OSVLRUTVBFIJMWUF7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KVOQZRWN5OSVLRUTVBFIJMWUF7/action/storage_attestation","attest_author":"https://pith.science/pith/KVOQZRWN5OSVLRUTVBFIJMWUF7/action/author_attestation","sign_citation":"https://pith.science/pith/KVOQZRWN5OSVLRUTVBFIJMWUF7/action/citation_signature","submit_replication":"https://pith.science/pith/KVOQZRWN5OSVLRUTVBFIJMWUF7/action/replication_record"}},"created_at":"2026-07-05T07:29:40.870174+00:00","updated_at":"2026-07-05T07:29:40.870174+00:00"}