{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:M5AHFKRACAZORUVVRMWF2RFRD2","short_pith_number":"pith:M5AHFKRA","schema_version":"1.0","canonical_sha256":"674072aa201032e8d2b58b2c5d44b11e8851902cdf0f897973fb31a9cde72780","source":{"kind":"arxiv","id":"2312.17225","version":3},"attestation_state":"computed","paper":{"title":"4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dejia Xu, Yao Zhao, Yunchao Wei, Yuyang Yin, Zhangyang Wang","submitted_at":"2023-12-28T18:53:39Z","abstract_excerpt":"Aided by text-to-image and text-to-video diffusion models, existing 4D content creation pipelines utilize score distillation sampling to optimize the entire dynamic 3D scene. However, as these pipelines generate 4D content from text or image inputs directly, they are constrained by limited motion capabilities and depend on unreliable prompt engineering for desired results. To address these problems, this work introduces \\textbf{4DGen}, a novel framework for grounded 4D content creation. We identify monocular video sequences as a key component in constructing the 4D content. Our pipeline facili"},"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":"2312.17225","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-28T18:53:39Z","cross_cats_sorted":[],"title_canon_sha256":"3868f53e8a13eb8faccc1a1c2b1458ce1a806866e424af56ce81e0690835b321","abstract_canon_sha256":"eb6d699162ab48517b61f9f187a7c6588b412513d6e071a75b579640c9888d9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:06.679760Z","signature_b64":"PJ9I+VWYl1cCN2ROsvwGyd95hpHrkrLaYtO/ViOFFPOWdgTlNoLvmkFJlpSUsTKd21vnTZcPIadulqYd/k7LBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"674072aa201032e8d2b58b2c5d44b11e8851902cdf0f897973fb31a9cde72780","last_reissued_at":"2026-07-05T09:44:06.679251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:06.679251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dejia Xu, Yao Zhao, Yunchao Wei, Yuyang Yin, Zhangyang Wang","submitted_at":"2023-12-28T18:53:39Z","abstract_excerpt":"Aided by text-to-image and text-to-video diffusion models, existing 4D content creation pipelines utilize score distillation sampling to optimize the entire dynamic 3D scene. However, as these pipelines generate 4D content from text or image inputs directly, they are constrained by limited motion capabilities and depend on unreliable prompt engineering for desired results. To address these problems, this work introduces \\textbf{4DGen}, a novel framework for grounded 4D content creation. We identify monocular video sequences as a key component in constructing the 4D content. Our pipeline facili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17225","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/2312.17225/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":"2312.17225","created_at":"2026-07-05T09:44:06.679306+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.17225v3","created_at":"2026-07-05T09:44:06.679306+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17225","created_at":"2026-07-05T09:44:06.679306+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5AHFKRACAZO","created_at":"2026-07-05T09:44:06.679306+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5AHFKRACAZORUVV","created_at":"2026-07-05T09:44:06.679306+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5AHFKRA","created_at":"2026-07-05T09:44:06.679306+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22131","citing_title":"Feed-forward Motion In-betweening for Any 4D","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02516","citing_title":"Alignment Is All You Need For X-to-4D Generation","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08688","citing_title":"PhysAgent: Automating Physics-Based 4D Synthesis via Trajectory-Grounded Multi-Agent Feedback","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26109","citing_title":"Helix4D: Complex 4D Mesh Generation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03890","citing_title":"A Survey on 3D Gaussian Splatting","ref_index":275,"is_internal_anchor":false},{"citing_arxiv_id":"2412.09176","citing_title":"LIVE-GS: LLM Powers Interactive VR Experience with Physics-Aware Gaussian Splatting","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19786","citing_title":"Fast 4D Mesh Generation by Spatio-Temporal Attention Chains","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":164,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":164,"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":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04527","citing_title":"Velox: Learning Representations of 4D Geometry and Appearance","ref_index":110,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M5AHFKRACAZORUVVRMWF2RFRD2","json":"https://pith.science/pith/M5AHFKRACAZORUVVRMWF2RFRD2.json","graph_json":"https://pith.science/api/pith-number/M5AHFKRACAZORUVVRMWF2RFRD2/graph.json","events_json":"https://pith.science/api/pith-number/M5AHFKRACAZORUVVRMWF2RFRD2/events.json","paper":"https://pith.science/paper/M5AHFKRA"},"agent_actions":{"view_html":"https://pith.science/pith/M5AHFKRACAZORUVVRMWF2RFRD2","download_json":"https://pith.science/pith/M5AHFKRACAZORUVVRMWF2RFRD2.json","view_paper":"https://pith.science/paper/M5AHFKRA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.17225&json=true","fetch_graph":"https://pith.science/api/pith-number/M5AHFKRACAZORUVVRMWF2RFRD2/graph.json","fetch_events":"https://pith.science/api/pith-number/M5AHFKRACAZORUVVRMWF2RFRD2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5AHFKRACAZORUVVRMWF2RFRD2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5AHFKRACAZORUVVRMWF2RFRD2/action/storage_attestation","attest_author":"https://pith.science/pith/M5AHFKRACAZORUVVRMWF2RFRD2/action/author_attestation","sign_citation":"https://pith.science/pith/M5AHFKRACAZORUVVRMWF2RFRD2/action/citation_signature","submit_replication":"https://pith.science/pith/M5AHFKRACAZORUVVRMWF2RFRD2/action/replication_record"}},"created_at":"2026-07-05T09:44:06.679306+00:00","updated_at":"2026-07-05T09:44:06.679306+00:00"}