{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IFY2YPZOGS64T76OJMB2WBZMH4","short_pith_number":"pith:IFY2YPZO","schema_version":"1.0","canonical_sha256":"4171ac3f2e34bdc9ffce4b03ab072c3f1f0eecfaba08a2100cdbdef261f44857","source":{"kind":"arxiv","id":"2307.01831","version":1},"attestation_state":"computed","paper":{"title":"DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Enze Xie, Lanqing Hong, Lewei Yao, Matthias Nie{\\ss}ner, Ruihang Chu, Shentong Mo, Zhenguo Li","submitted_at":"2023-07-04T17:15:46Z","abstract_excerpt":"Recent Diffusion Transformers (e.g., DiT) have demonstrated their powerful effectiveness in generating high-quality 2D images. However, it is still being determined whether the Transformer architecture performs equally well in 3D shape generation, as previous 3D diffusion methods mostly adopted the U-Net architecture. To bridge this gap, we propose a novel Diffusion Transformer for 3D shape generation, namely DiT-3D, which can directly operate the denoising process on voxelized point clouds using plain Transformers. Compared to existing U-Net approaches, our DiT-3D is more scalable in model si"},"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":"2307.01831","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-04T17:15:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f23dd42b4fa11d364a55be5fc0f62b15923add59a3a7fce94d29c8fa5188f7ad","abstract_canon_sha256":"4f484edd244fa1d4704c2d6d08d7d49f5f1cc65d717d609054ce2516cba08f20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:01.551575Z","signature_b64":"ECwXkIblNdSpdK5DskBP7yApm6DEmhlQzKjlSac23JDGGxIQ8dqlecDJuG6ioYhb+rX7uc97rBTGnhsQC9NhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4171ac3f2e34bdc9ffce4b03ab072c3f1f0eecfaba08a2100cdbdef261f44857","last_reissued_at":"2026-07-05T06:28:01.550174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:01.550174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Enze Xie, Lanqing Hong, Lewei Yao, Matthias Nie{\\ss}ner, Ruihang Chu, Shentong Mo, Zhenguo Li","submitted_at":"2023-07-04T17:15:46Z","abstract_excerpt":"Recent Diffusion Transformers (e.g., DiT) have demonstrated their powerful effectiveness in generating high-quality 2D images. However, it is still being determined whether the Transformer architecture performs equally well in 3D shape generation, as previous 3D diffusion methods mostly adopted the U-Net architecture. To bridge this gap, we propose a novel Diffusion Transformer for 3D shape generation, namely DiT-3D, which can directly operate the denoising process on voxelized point clouds using plain Transformers. Compared to existing U-Net approaches, our DiT-3D is more scalable in model si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01831","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/2307.01831/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":"2307.01831","created_at":"2026-07-05T06:28:01.550795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.01831v1","created_at":"2026-07-05T06:28:01.550795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01831","created_at":"2026-07-05T06:28:01.550795+00:00"},{"alias_kind":"pith_short_12","alias_value":"IFY2YPZOGS64","created_at":"2026-07-05T06:28:01.550795+00:00"},{"alias_kind":"pith_short_16","alias_value":"IFY2YPZOGS64T76O","created_at":"2026-07-05T06:28:01.550795+00:00"},{"alias_kind":"pith_short_8","alias_value":"IFY2YPZO","created_at":"2026-07-05T06:28:01.550795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.23483","citing_title":"Stable-Sim2Real: Exploring Simulation of Real-Captured 3D Data with Two-Stage Depth Diffusion","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IFY2YPZOGS64T76OJMB2WBZMH4","json":"https://pith.science/pith/IFY2YPZOGS64T76OJMB2WBZMH4.json","graph_json":"https://pith.science/api/pith-number/IFY2YPZOGS64T76OJMB2WBZMH4/graph.json","events_json":"https://pith.science/api/pith-number/IFY2YPZOGS64T76OJMB2WBZMH4/events.json","paper":"https://pith.science/paper/IFY2YPZO"},"agent_actions":{"view_html":"https://pith.science/pith/IFY2YPZOGS64T76OJMB2WBZMH4","download_json":"https://pith.science/pith/IFY2YPZOGS64T76OJMB2WBZMH4.json","view_paper":"https://pith.science/paper/IFY2YPZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.01831&json=true","fetch_graph":"https://pith.science/api/pith-number/IFY2YPZOGS64T76OJMB2WBZMH4/graph.json","fetch_events":"https://pith.science/api/pith-number/IFY2YPZOGS64T76OJMB2WBZMH4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IFY2YPZOGS64T76OJMB2WBZMH4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IFY2YPZOGS64T76OJMB2WBZMH4/action/storage_attestation","attest_author":"https://pith.science/pith/IFY2YPZOGS64T76OJMB2WBZMH4/action/author_attestation","sign_citation":"https://pith.science/pith/IFY2YPZOGS64T76OJMB2WBZMH4/action/citation_signature","submit_replication":"https://pith.science/pith/IFY2YPZOGS64T76OJMB2WBZMH4/action/replication_record"}},"created_at":"2026-07-05T06:28:01.550795+00:00","updated_at":"2026-07-05T06:28:01.550795+00:00"}