{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QEHABAGLK7E2FKHSYWUJKPZTZM","short_pith_number":"pith:QEHABAGL","schema_version":"1.0","canonical_sha256":"810e0080cb57c9a2a8f2c5a8953f33cb15df0e368e3b136ca6a59ae0674b51e8","source":{"kind":"arxiv","id":"2503.23022","version":1},"attestation_state":"computed","paper":{"title":"MeshCraft: Exploring Efficient and Controllable Mesh Generation with Flow-based DiTs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Di Huang, Junyi Chen, Wanli Ouyang, Xianglong He, Xiaoshui Huang, Yangguang Li, Zexiang Liu","submitted_at":"2025-03-29T09:21:50Z","abstract_excerpt":"In the domain of 3D content creation, achieving optimal mesh topology through AI models has long been a pursuit for 3D artists. Previous methods, such as MeshGPT, have explored the generation of ready-to-use 3D objects via mesh auto-regressive techniques. While these methods produce visually impressive results, their reliance on token-by-token predictions in the auto-regressive process leads to several significant limitations. These include extremely slow generation speeds and an uncontrollable number of mesh faces. In this paper, we introduce MeshCraft, a novel framework for efficient and con"},"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":"2503.23022","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-29T09:21:50Z","cross_cats_sorted":[],"title_canon_sha256":"d8ac99e424308f2620ef269c9e34bb4c1e81d9454fc66ca922e4e6bebe902534","abstract_canon_sha256":"07411d6626eb88e15ba4a674a7fd64609bc8ffcbdd3f23a961c4bca298ee7984"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:29.235685Z","signature_b64":"Wqirs8kgYMDIOWbrJJ6Zcg+PKfdkDaspsl5W15pDm5Yd4I8u75aqJIswzTQ2A23zQQJ7cuiusMnpiYIlBQIeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"810e0080cb57c9a2a8f2c5a8953f33cb15df0e368e3b136ca6a59ae0674b51e8","last_reissued_at":"2026-07-05T10:41:29.235208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:29.235208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MeshCraft: Exploring Efficient and Controllable Mesh Generation with Flow-based DiTs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Di Huang, Junyi Chen, Wanli Ouyang, Xianglong He, Xiaoshui Huang, Yangguang Li, Zexiang Liu","submitted_at":"2025-03-29T09:21:50Z","abstract_excerpt":"In the domain of 3D content creation, achieving optimal mesh topology through AI models has long been a pursuit for 3D artists. Previous methods, such as MeshGPT, have explored the generation of ready-to-use 3D objects via mesh auto-regressive techniques. While these methods produce visually impressive results, their reliance on token-by-token predictions in the auto-regressive process leads to several significant limitations. These include extremely slow generation speeds and an uncontrollable number of mesh faces. In this paper, we introduce MeshCraft, a novel framework for efficient and con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23022","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/2503.23022/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":"2503.23022","created_at":"2026-07-05T10:41:29.235265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.23022v1","created_at":"2026-07-05T10:41:29.235265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23022","created_at":"2026-07-05T10:41:29.235265+00:00"},{"alias_kind":"pith_short_12","alias_value":"QEHABAGLK7E2","created_at":"2026-07-05T10:41:29.235265+00:00"},{"alias_kind":"pith_short_16","alias_value":"QEHABAGLK7E2FKHS","created_at":"2026-07-05T10:41:29.235265+00:00"},{"alias_kind":"pith_short_8","alias_value":"QEHABAGL","created_at":"2026-07-05T10:41:29.235265+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23489","citing_title":"MeshFlow: Mesh Generation with Equivariant Flow Matching","ref_index":125,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04621","citing_title":"MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31777","citing_title":"Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23629","citing_title":"From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation","ref_index":147,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23629","citing_title":"From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation","ref_index":147,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QEHABAGLK7E2FKHSYWUJKPZTZM","json":"https://pith.science/pith/QEHABAGLK7E2FKHSYWUJKPZTZM.json","graph_json":"https://pith.science/api/pith-number/QEHABAGLK7E2FKHSYWUJKPZTZM/graph.json","events_json":"https://pith.science/api/pith-number/QEHABAGLK7E2FKHSYWUJKPZTZM/events.json","paper":"https://pith.science/paper/QEHABAGL"},"agent_actions":{"view_html":"https://pith.science/pith/QEHABAGLK7E2FKHSYWUJKPZTZM","download_json":"https://pith.science/pith/QEHABAGLK7E2FKHSYWUJKPZTZM.json","view_paper":"https://pith.science/paper/QEHABAGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.23022&json=true","fetch_graph":"https://pith.science/api/pith-number/QEHABAGLK7E2FKHSYWUJKPZTZM/graph.json","fetch_events":"https://pith.science/api/pith-number/QEHABAGLK7E2FKHSYWUJKPZTZM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QEHABAGLK7E2FKHSYWUJKPZTZM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QEHABAGLK7E2FKHSYWUJKPZTZM/action/storage_attestation","attest_author":"https://pith.science/pith/QEHABAGLK7E2FKHSYWUJKPZTZM/action/author_attestation","sign_citation":"https://pith.science/pith/QEHABAGLK7E2FKHSYWUJKPZTZM/action/citation_signature","submit_replication":"https://pith.science/pith/QEHABAGLK7E2FKHSYWUJKPZTZM/action/replication_record"}},"created_at":"2026-07-05T10:41:29.235265+00:00","updated_at":"2026-07-05T10:41:29.235265+00:00"}