{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2KSQKR5GVKHBAYN32RKDAAYYRJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"96be00091563b2de602b346b0c76a70c54d96c9ef69bb79de500a8ce3b3b2b68","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T13:58:38Z","title_canon_sha256":"443f06edc7fa6690c52d391606e40ad8d719a0f4504a7a26de7b2284a959bdea"},"schema_version":"1.0","source":{"id":"2412.01506","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01506","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01506v3","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01506","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"pith_short_12","alias_value":"2KSQKR5GVKHB","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2KSQKR5GVKHBAYN3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2KSQKR5G","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:2a06a6f6c88b6e53910ccdfdf4831bfe0020f4cfa6dc41571f3bea6b0ee70e0d","target":"graph","created_at":"2026-05-17T23:38:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our model generates high-quality results with text or image conditions, significantly surpassing existing methods, including recent ones at similar scales."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The integration of a sparsely-populated 3D grid with dense multiview visual features from a vision foundation model comprehensively captures both structural geometry and textural appearance information while maintaining decoding flexibility."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SLAT provides a unified 3D latent representation enabling versatile high-quality generation across multiple output formats from text or image inputs."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A structured latent that merges sparse 3D grids with dense multiview features supports high-quality generation of 3D assets in multiple output formats from text or image input."}],"snapshot_sha256":"ba52f5368bf37445b0ea7ad2f8587a46f42b06282058f3f1780ddaca9cbd6231"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"2fb8040140c7f52b28f5d73f2ea22f598eb5d2c2696eb6765c1ff4ef87346ac1"},"paper":{"abstract_excerpt":"We introduce a novel 3D generation method for versatile and high-quality 3D asset creation. The cornerstone is a unified Structured LATent (SLAT) representation which allows decoding to different output formats, such as Radiance Fields, 3D Gaussians, and meshes. This is achieved by integrating a sparsely-populated 3D grid with dense multiview visual features extracted from a powerful vision foundation model, comprehensively capturing both structural (geometry) and textural (appearance) information while maintaining flexibility during decoding. We employ rectified flow transformers tailored for","authors_text":"Bowen Zhang, Dong Chen, Jianfeng Xiang, Jiaolong Yang, Ruicheng Wang, Sicheng Xu, Xin Tong, Yu Deng, Zelong Lv","cross_cats":[],"headline":"A structured latent that merges sparse 3D grids with dense multiview features supports high-quality generation of 3D assets in multiple output formats from text or image input.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T13:58:38Z","title":"Structured 3D Latents for Scalable and Versatile 3D Generation"},"references":{"count":117,"internal_anchors":6,"resolved_work":117,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Gpt-4o system card. 2024. 6, 16","work_id":"31f4f27a-bda9-4fa5-9486-8dd8a76923d3","year":2024},{"cited_arxiv_id":"2303.08774","doi":"","is_internal_anchor":true,"ref_index":2,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Build- ing normalizing flows with stochastic interpolants","work_id":"18c42973-7784-4a94-9eb5-a5c41d8ae522","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Improving image generation with better captions","work_id":"283b326a-614b-42d1-b67f-4040cddad7e5","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Demystifying mmd gans","work_id":"d3a22946-30b0-4329-896b-dff78f4495e1","year":2018}],"snapshot_sha256":"3f8bfa1c68f0548796791686cf0bdacb503eaa262650f2c63bde43a220401fbc"},"source":{"id":"2412.01506","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T15:05:40.004428Z","id":"6e031692-e933-4e9f-be68-994e503b3da1","model_set":{"reader":"grok-4.3"},"one_line_summary":"SLAT provides a unified 3D latent representation enabling versatile high-quality generation across multiple output formats from text or image inputs.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A structured latent that merges sparse 3D grids with dense multiview features supports high-quality generation of 3D assets in multiple output formats from text or image input.","strongest_claim":"Our model generates high-quality results with text or image conditions, significantly surpassing existing methods, including recent ones at similar scales.","weakest_assumption":"The integration of a sparsely-populated 3D grid with dense multiview visual features from a vision foundation model comprehensively captures both structural geometry and textural appearance information while maintaining decoding flexibility."}},"verdict_id":"6e031692-e933-4e9f-be68-994e503b3da1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:786b2c054db82b1dd23baace2071b48ab5ce7272b889ab47f974aed5792c4eea","target":"record","created_at":"2026-05-17T23:38:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"96be00091563b2de602b346b0c76a70c54d96c9ef69bb79de500a8ce3b3b2b68","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T13:58:38Z","title_canon_sha256":"443f06edc7fa6690c52d391606e40ad8d719a0f4504a7a26de7b2284a959bdea"},"schema_version":"1.0","source":{"id":"2412.01506","kind":"arxiv","version":3}},"canonical_sha256":"d2a50547a6aa8e1061bbd4543003188a5b606ad9a09f52e95f342425d0d1088b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2a50547a6aa8e1061bbd4543003188a5b606ad9a09f52e95f342425d0d1088b","first_computed_at":"2026-05-17T23:38:47.485867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:47.485867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H3TcVYNgx/UGsoyTprnnYD/3kLuAxB++1AXaYHj1gcOxUSTFpoGCxAvi5t5a0A2tzfF4yawwaYW6tmeaHPjmCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:47.486663Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01506","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:786b2c054db82b1dd23baace2071b48ab5ce7272b889ab47f974aed5792c4eea","sha256:2a06a6f6c88b6e53910ccdfdf4831bfe0020f4cfa6dc41571f3bea6b0ee70e0d"],"state_sha256":"c694503b95cf6ced9c45dc4254bf7440502eef417c0f3fd1b5ebc0316ff21a8f"}