{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7CBV6XXJGVSL2NFJPQLOLX56DS","short_pith_number":"pith:7CBV6XXJ","schema_version":"1.0","canonical_sha256":"f8835f5ee93564bd34a97c16e5dfbe1ca4583aa86e195e6665fe62aa6181efe1","source":{"kind":"arxiv","id":"2411.02319","version":2},"attestation_state":"computed","paper":{"title":"GenXD: Generating Any 3D and 4D Scenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chung-Ching Lin, Gim Hee Lee, Jianfeng Wang, Kevin Lin, Lijuan Wang, Linjie Li, Yuyang Zhao, Zhengyuan Yang, Zhiwen Yan","submitted_at":"2024-11-04T17:45:44Z","abstract_excerpt":"Recent developments in 2D visual generation have been remarkably successful. However, 3D and 4D generation remain challenging in real-world applications due to the lack of large-scale 4D data and effective model design. In this paper, we propose to jointly investigate general 3D and 4D generation by leveraging camera and object movements commonly observed in daily life. Due to the lack of real-world 4D data in the community, we first propose a data curation pipeline to obtain camera poses and object motion strength from videos. Based on this pipeline, we introduce a large-scale real-world 4D s"},"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":"2411.02319","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-04T17:45:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"673857c247d0b35e375ccfd12ed574a75e6afa7aefd72099e36707dffcfe9a13","abstract_canon_sha256":"563df335ac275fe8db6312325b6193a37ce4d6b3465e84c0f9732849452b8271"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:11.171864Z","signature_b64":"NT+GuQ9FqFXASLW/Ynz0r65mnENdX58HoskQxCL07SBK8xhNaGHLEuqv8TSLsrmRSXTx+DEu1GX2hEBs0rzOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8835f5ee93564bd34a97c16e5dfbe1ca4583aa86e195e6665fe62aa6181efe1","last_reissued_at":"2026-07-05T09:31:11.171278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:11.171278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenXD: Generating Any 3D and 4D Scenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chung-Ching Lin, Gim Hee Lee, Jianfeng Wang, Kevin Lin, Lijuan Wang, Linjie Li, Yuyang Zhao, Zhengyuan Yang, Zhiwen Yan","submitted_at":"2024-11-04T17:45:44Z","abstract_excerpt":"Recent developments in 2D visual generation have been remarkably successful. However, 3D and 4D generation remain challenging in real-world applications due to the lack of large-scale 4D data and effective model design. In this paper, we propose to jointly investigate general 3D and 4D generation by leveraging camera and object movements commonly observed in daily life. Due to the lack of real-world 4D data in the community, we first propose a data curation pipeline to obtain camera poses and object motion strength from videos. Based on this pipeline, we introduce a large-scale real-world 4D s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02319","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/2411.02319/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":"2411.02319","created_at":"2026-07-05T09:31:11.171366+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.02319v2","created_at":"2026-07-05T09:31:11.171366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02319","created_at":"2026-07-05T09:31:11.171366+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CBV6XXJGVSL","created_at":"2026-07-05T09:31:11.171366+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CBV6XXJGVSL2NFJ","created_at":"2026-07-05T09:31:11.171366+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CBV6XXJ","created_at":"2026-07-05T09:31:11.171366+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05373","citing_title":"PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2602.04876","citing_title":"PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generation","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00503","citing_title":"Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00062","citing_title":"World Simulation with Video Foundation Models for Physical AI","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07990","citing_title":"SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07390","citing_title":"ST-Gen4D: Embedding 4D Spatiotemporal Cognition into World Model for 4D Generation","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7CBV6XXJGVSL2NFJPQLOLX56DS","json":"https://pith.science/pith/7CBV6XXJGVSL2NFJPQLOLX56DS.json","graph_json":"https://pith.science/api/pith-number/7CBV6XXJGVSL2NFJPQLOLX56DS/graph.json","events_json":"https://pith.science/api/pith-number/7CBV6XXJGVSL2NFJPQLOLX56DS/events.json","paper":"https://pith.science/paper/7CBV6XXJ"},"agent_actions":{"view_html":"https://pith.science/pith/7CBV6XXJGVSL2NFJPQLOLX56DS","download_json":"https://pith.science/pith/7CBV6XXJGVSL2NFJPQLOLX56DS.json","view_paper":"https://pith.science/paper/7CBV6XXJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.02319&json=true","fetch_graph":"https://pith.science/api/pith-number/7CBV6XXJGVSL2NFJPQLOLX56DS/graph.json","fetch_events":"https://pith.science/api/pith-number/7CBV6XXJGVSL2NFJPQLOLX56DS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CBV6XXJGVSL2NFJPQLOLX56DS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CBV6XXJGVSL2NFJPQLOLX56DS/action/storage_attestation","attest_author":"https://pith.science/pith/7CBV6XXJGVSL2NFJPQLOLX56DS/action/author_attestation","sign_citation":"https://pith.science/pith/7CBV6XXJGVSL2NFJPQLOLX56DS/action/citation_signature","submit_replication":"https://pith.science/pith/7CBV6XXJGVSL2NFJPQLOLX56DS/action/replication_record"}},"created_at":"2026-07-05T09:31:11.171366+00:00","updated_at":"2026-07-05T09:31:11.171366+00:00"}