{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MV5RKUXKVL5MHTE4MYACZQV7QX","short_pith_number":"pith:MV5RKUXK","schema_version":"1.0","canonical_sha256":"657b1552eaaafac3cc9c66002cc2bf85e225c1306ed4f5cde7b5d6c70852eb8c","source":{"kind":"arxiv","id":"2606.04621","version":1},"attestation_state":"computed","paper":{"title":"MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Antoine Toisoul, Ping Tan, Rakesh Ranjan, Roman Shapovalov, Tom Monnier, Weiyu Li","submitted_at":"2026-06-03T08:57:15Z","abstract_excerpt":"We present MeshFlow, a new method for generating artist-like 3D meshes. Current mesh generators often adopt Auto-Regressive (AR) next-token prediction, a natural choice given the discrete nature of mesh topology. However, AR methods scale poorly because the inference cost is quadratic in mesh size. They also require discretizing the vertex coordinates, which introduces quantization errors. To address these challenges, we introduce a Variational Autoencoder (VAE) that, supervised with a contrastive loss, represents both continuous vertex positions and discrete connectivity in a continuous laten"},"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":"2606.04621","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T08:57:15Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"fe9d7950655f8862f5a29dc6503e2e968b38399ac190dc39ea2f2f226d0e7ceb","abstract_canon_sha256":"035831510201c47f380166b4bb631c1ac0e786f447513d648b255f33f2e0fe62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:21.734677Z","signature_b64":"V4P7DmVGNgEAiiiBmFAuY7Q0vNn0O4Ytp8ZdrURvPS16niuZXDQ5snG3XJc6+L4eOpyWFhk7AihZSwTnE1WzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"657b1552eaaafac3cc9c66002cc2bf85e225c1306ed4f5cde7b5d6c70852eb8c","last_reissued_at":"2026-06-04T01:09:21.733934Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:21.733934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Antoine Toisoul, Ping Tan, Rakesh Ranjan, Roman Shapovalov, Tom Monnier, Weiyu Li","submitted_at":"2026-06-03T08:57:15Z","abstract_excerpt":"We present MeshFlow, a new method for generating artist-like 3D meshes. Current mesh generators often adopt Auto-Regressive (AR) next-token prediction, a natural choice given the discrete nature of mesh topology. However, AR methods scale poorly because the inference cost is quadratic in mesh size. They also require discretizing the vertex coordinates, which introduces quantization errors. To address these challenges, we introduce a Variational Autoencoder (VAE) that, supervised with a contrastive loss, represents both continuous vertex positions and discrete connectivity in a continuous laten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04621","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/2606.04621/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":"2606.04621","created_at":"2026-06-04T01:09:21.734055+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04621v1","created_at":"2026-06-04T01:09:21.734055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04621","created_at":"2026-06-04T01:09:21.734055+00:00"},{"alias_kind":"pith_short_12","alias_value":"MV5RKUXKVL5M","created_at":"2026-06-04T01:09:21.734055+00:00"},{"alias_kind":"pith_short_16","alias_value":"MV5RKUXKVL5MHTE4","created_at":"2026-06-04T01:09:21.734055+00:00"},{"alias_kind":"pith_short_8","alias_value":"MV5RKUXK","created_at":"2026-06-04T01:09:21.734055+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MV5RKUXKVL5MHTE4MYACZQV7QX","json":"https://pith.science/pith/MV5RKUXKVL5MHTE4MYACZQV7QX.json","graph_json":"https://pith.science/api/pith-number/MV5RKUXKVL5MHTE4MYACZQV7QX/graph.json","events_json":"https://pith.science/api/pith-number/MV5RKUXKVL5MHTE4MYACZQV7QX/events.json","paper":"https://pith.science/paper/MV5RKUXK"},"agent_actions":{"view_html":"https://pith.science/pith/MV5RKUXKVL5MHTE4MYACZQV7QX","download_json":"https://pith.science/pith/MV5RKUXKVL5MHTE4MYACZQV7QX.json","view_paper":"https://pith.science/paper/MV5RKUXK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04621&json=true","fetch_graph":"https://pith.science/api/pith-number/MV5RKUXKVL5MHTE4MYACZQV7QX/graph.json","fetch_events":"https://pith.science/api/pith-number/MV5RKUXKVL5MHTE4MYACZQV7QX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MV5RKUXKVL5MHTE4MYACZQV7QX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MV5RKUXKVL5MHTE4MYACZQV7QX/action/storage_attestation","attest_author":"https://pith.science/pith/MV5RKUXKVL5MHTE4MYACZQV7QX/action/author_attestation","sign_citation":"https://pith.science/pith/MV5RKUXKVL5MHTE4MYACZQV7QX/action/citation_signature","submit_replication":"https://pith.science/pith/MV5RKUXKVL5MHTE4MYACZQV7QX/action/replication_record"}},"created_at":"2026-06-04T01:09:21.734055+00:00","updated_at":"2026-06-04T01:09:21.734055+00:00"}