{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MXB5A2GN3FO2V6S5YAT2X5CPZP","short_pith_number":"pith:MXB5A2GN","schema_version":"1.0","canonical_sha256":"65c3d068cdd95daafa5dc027abf44fcbffcced2c5039c54c3abdd90f9b07f35f","source":{"kind":"arxiv","id":"2512.14692","version":1},"attestation_state":"computed","paper":{"title":"Native and Compact Structured Latents for 3D Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hao Zhao, Hongyuan Zhu, Jianfeng Xiang, Jiaolong Yang, Nicholas Jing Yuan, Ruicheng Wang, Sicheng Xu, Xiaoxue Chen, Yu Deng, Yue Dong, Zelong Lv","submitted_at":"2025-12-16T18:58:28Z","abstract_excerpt":"Recent advancements in 3D generative modeling have significantly improved the generation realism, yet the field is still hampered by existing representations, which struggle to capture assets with complex topologies and detailed appearance. This paper present an approach for learning a structured latent representation from native 3D data to address this challenge. At its core is a new sparse voxel structure called O-Voxel, an omni-voxel representation that encodes both geometry and appearance. O-Voxel can robustly model arbitrary topology, including open, non-manifold, and fully-enclosed surfa"},"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":"2512.14692","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-16T18:58:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6a4a24520d6a364efdc94e5956e4ff5267c308ac3f6ec04125d8c5a0c1c47f12","abstract_canon_sha256":"acb78db1ca29404e62f1b29712e9d36e151a045c8ce40ddc40f597b5124a094f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T05:14:18.387361Z","signature_b64":"/kFgLFUVqytirCUsvDGprPMd9Wa0tY9+qHa+rmpnOJb35UtAzrpkYolrd9ZAAroE57v33o9zLDK66m8snR9uDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65c3d068cdd95daafa5dc027abf44fcbffcced2c5039c54c3abdd90f9b07f35f","last_reissued_at":"2026-05-21T05:14:18.384602Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T05:14:18.384602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Native and Compact Structured Latents for 3D Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hao Zhao, Hongyuan Zhu, Jianfeng Xiang, Jiaolong Yang, Nicholas Jing Yuan, Ruicheng Wang, Sicheng Xu, Xiaoxue Chen, Yu Deng, Yue Dong, Zelong Lv","submitted_at":"2025-12-16T18:58:28Z","abstract_excerpt":"Recent advancements in 3D generative modeling have significantly improved the generation realism, yet the field is still hampered by existing representations, which struggle to capture assets with complex topologies and detailed appearance. This paper present an approach for learning a structured latent representation from native 3D data to address this challenge. At its core is a new sparse voxel structure called O-Voxel, an omni-voxel representation that encodes both geometry and appearance. O-Voxel can robustly model arbitrary topology, including open, non-manifold, and fully-enclosed surfa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.14692","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/2512.14692/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":"2512.14692","created_at":"2026-05-21T05:14:18.384743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.14692v1","created_at":"2026-05-21T05:14:18.384743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.14692","created_at":"2026-05-21T05:14:18.384743+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXB5A2GN3FO2","created_at":"2026-05-21T05:14:18.384743+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXB5A2GN3FO2V6S5","created_at":"2026-05-21T05:14:18.384743+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXB5A2GN","created_at":"2026-05-21T05:14:18.384743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":25,"sample":[{"citing_arxiv_id":"2605.21572","citing_title":"PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21121","citing_title":"ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21472","citing_title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16355","citing_title":"Generative 3D Gaussians with Learned Density Control","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18680","citing_title":"CMAG: Concept-Scaffolded Retrieval for Marketplace Avatar Generation","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18063","citing_title":"The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Counting","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16745","citing_title":"EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13862","citing_title":"Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13129","citing_title":"Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26509","citing_title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","ref_index":102,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09606","citing_title":"On the Generation and Mitigation of Harmful Geometry in Image-to-3D Models","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10887","citing_title":"Count Anything at Any Granularity","ref_index":74,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10922","citing_title":"Pixal3D: Pixel-Aligned 3D Generation from Images","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23629","citing_title":"From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26509","citing_title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","ref_index":102,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23629","citing_title":"From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18468","citing_title":"Asset Harvester: Extracting 3D Assets from Autonomous Driving Logs for Simulation","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11331","citing_title":"Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale","ref_index":77,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26509","citing_title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","ref_index":102,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07385","citing_title":"Velocity-Space 3D Asset Editing","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07971","citing_title":"DVD: Discrete Voxel Diffusion for 3D Generation and Editing","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09231","citing_title":"Hitem3D 2.0: Multi-View Guided Native 3D Texture Generation","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05182","citing_title":"LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14302","citing_title":"Geometrically Consistent Multi-View Scene Generation from Freehand Sketches","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03105","citing_title":"Pose Tracking with a Foundation Pose Model and an Ensemble Directional Kalman Filter","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MXB5A2GN3FO2V6S5YAT2X5CPZP","json":"https://pith.science/pith/MXB5A2GN3FO2V6S5YAT2X5CPZP.json","graph_json":"https://pith.science/api/pith-number/MXB5A2GN3FO2V6S5YAT2X5CPZP/graph.json","events_json":"https://pith.science/api/pith-number/MXB5A2GN3FO2V6S5YAT2X5CPZP/events.json","paper":"https://pith.science/paper/MXB5A2GN"},"agent_actions":{"view_html":"https://pith.science/pith/MXB5A2GN3FO2V6S5YAT2X5CPZP","download_json":"https://pith.science/pith/MXB5A2GN3FO2V6S5YAT2X5CPZP.json","view_paper":"https://pith.science/paper/MXB5A2GN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.14692&json=true","fetch_graph":"https://pith.science/api/pith-number/MXB5A2GN3FO2V6S5YAT2X5CPZP/graph.json","fetch_events":"https://pith.science/api/pith-number/MXB5A2GN3FO2V6S5YAT2X5CPZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXB5A2GN3FO2V6S5YAT2X5CPZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXB5A2GN3FO2V6S5YAT2X5CPZP/action/storage_attestation","attest_author":"https://pith.science/pith/MXB5A2GN3FO2V6S5YAT2X5CPZP/action/author_attestation","sign_citation":"https://pith.science/pith/MXB5A2GN3FO2V6S5YAT2X5CPZP/action/citation_signature","submit_replication":"https://pith.science/pith/MXB5A2GN3FO2V6S5YAT2X5CPZP/action/replication_record"}},"created_at":"2026-05-21T05:14:18.384743+00:00","updated_at":"2026-05-21T05:14:18.384743+00:00"}