{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WZAAOOSLJE3HIONRW4EBF7NVWS","short_pith_number":"pith:WZAAOOSL","schema_version":"1.0","canonical_sha256":"b640073a4b49367439b1b70812fdb5b4b60e4a7f72922635538db0cf7756fce7","source":{"kind":"arxiv","id":"2207.10228","version":1},"attestation_state":"computed","paper":{"title":"MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baosheng Yu, Fazhi He, Jing Zhang, Shanshan Zhao, Yaqian Liang","submitted_at":"2022-07-20T23:33:22Z","abstract_excerpt":"Recently, self-supervised pre-training has advanced Vision Transformers on various tasks w.r.t. different data modalities, e.g., image and 3D point cloud data. In this paper, we explore this learning paradigm for 3D mesh data analysis based on Transformers. Since applying Transformer architectures to new modalities is usually non-trivial, we first adapt Vision Transformer to 3D mesh data processing, i.e., Mesh Transformer. In specific, we divide a mesh into several non-overlapping local patches with each containing the same number of faces and use the 3D position of each patch's center point t"},"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":"2207.10228","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-20T23:33:22Z","cross_cats_sorted":[],"title_canon_sha256":"3dcf69edb2866e857386e735f2b773e3301c08bc3034a67b8481648b75b75894","abstract_canon_sha256":"f187de26dfe3aac59013ebd1d5efb6d2c43d1a6d4f4ae39904008fe4f4957913"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:42:22.612874Z","signature_b64":"JKi5qAU3YMJRPZmPPCLnk1ko6C47uLBUeq3EjcQHdJjRCjghrRipr/RGrjnLvb2I+t28REc3T6D7lNrco+faAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b640073a4b49367439b1b70812fdb5b4b60e4a7f72922635538db0cf7756fce7","last_reissued_at":"2026-07-05T04:42:22.612444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:42:22.612444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baosheng Yu, Fazhi He, Jing Zhang, Shanshan Zhao, Yaqian Liang","submitted_at":"2022-07-20T23:33:22Z","abstract_excerpt":"Recently, self-supervised pre-training has advanced Vision Transformers on various tasks w.r.t. different data modalities, e.g., image and 3D point cloud data. In this paper, we explore this learning paradigm for 3D mesh data analysis based on Transformers. Since applying Transformer architectures to new modalities is usually non-trivial, we first adapt Vision Transformer to 3D mesh data processing, i.e., Mesh Transformer. In specific, we divide a mesh into several non-overlapping local patches with each containing the same number of faces and use the 3D position of each patch's center point t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.10228","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/2207.10228/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":"2207.10228","created_at":"2026-07-05T04:42:22.612509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.10228v1","created_at":"2026-07-05T04:42:22.612509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.10228","created_at":"2026-07-05T04:42:22.612509+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZAAOOSLJE3H","created_at":"2026-07-05T04:42:22.612509+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZAAOOSLJE3HIONR","created_at":"2026-07-05T04:42:22.612509+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZAAOOSL","created_at":"2026-07-05T04:42:22.612509+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.09597","citing_title":"Reducing the Sensitivity of Neural Physics Simulators to Mesh Topology via Pretraining","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WZAAOOSLJE3HIONRW4EBF7NVWS","json":"https://pith.science/pith/WZAAOOSLJE3HIONRW4EBF7NVWS.json","graph_json":"https://pith.science/api/pith-number/WZAAOOSLJE3HIONRW4EBF7NVWS/graph.json","events_json":"https://pith.science/api/pith-number/WZAAOOSLJE3HIONRW4EBF7NVWS/events.json","paper":"https://pith.science/paper/WZAAOOSL"},"agent_actions":{"view_html":"https://pith.science/pith/WZAAOOSLJE3HIONRW4EBF7NVWS","download_json":"https://pith.science/pith/WZAAOOSLJE3HIONRW4EBF7NVWS.json","view_paper":"https://pith.science/paper/WZAAOOSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.10228&json=true","fetch_graph":"https://pith.science/api/pith-number/WZAAOOSLJE3HIONRW4EBF7NVWS/graph.json","fetch_events":"https://pith.science/api/pith-number/WZAAOOSLJE3HIONRW4EBF7NVWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZAAOOSLJE3HIONRW4EBF7NVWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZAAOOSLJE3HIONRW4EBF7NVWS/action/storage_attestation","attest_author":"https://pith.science/pith/WZAAOOSLJE3HIONRW4EBF7NVWS/action/author_attestation","sign_citation":"https://pith.science/pith/WZAAOOSLJE3HIONRW4EBF7NVWS/action/citation_signature","submit_replication":"https://pith.science/pith/WZAAOOSLJE3HIONRW4EBF7NVWS/action/replication_record"}},"created_at":"2026-07-05T04:42:22.612509+00:00","updated_at":"2026-07-05T04:42:22.612509+00:00"}