{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:T4DUCSCYEKMPP4GLT2ZI52AMX2","short_pith_number":"pith:T4DUCSCY","schema_version":"1.0","canonical_sha256":"9f074148582298f7f0cb9eb28ee80cbe9b2c55d9d466494ec05ffdf9bb3d3b12","source":{"kind":"arxiv","id":"2002.10880","version":1},"attestation_state":"computed","paper":{"title":"PolyGen: An Autoregressive Generative Model of 3D Meshes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ML"],"primary_cat":"cs.GR","authors_text":"Charlie Nash, Peter W. Battaglia, S. M. Ali Eslami, Yaroslav Ganin","submitted_at":"2020-02-23T17:16:34Z","abstract_excerpt":"Polygon meshes are an efficient representation of 3D geometry, and are of central importance in computer graphics, robotics and games development. Existing learning-based approaches have avoided the challenges of working with 3D meshes, instead using alternative object representations that are more compatible with neural architectures and training approaches. We present an approach which models the mesh directly, predicting mesh vertices and faces sequentially using a Transformer-based architecture. Our model can condition on a range of inputs, including object classes, voxels, and images, and"},"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":"2002.10880","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2020-02-23T17:16:34Z","cross_cats_sorted":["cs.CV","cs.LG","stat.ML"],"title_canon_sha256":"69f2144e0b948ee364520efdb98cbb33467c235fa0629b69eef77d99507f1be4","abstract_canon_sha256":"56aaa47fc6c6c45e8ff3f37679c7595be646949aaf2d5ae99314b7e75a316441"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:49.464134Z","signature_b64":"/JdUdR3/3ohSABDdVPeuK7BmDbKqHVGyL8UIKx8o080WhSY5CMRLEJFse5VRLNwoiCrx7HxQK3+0uIRPRD2HDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f074148582298f7f0cb9eb28ee80cbe9b2c55d9d466494ec05ffdf9bb3d3b12","last_reissued_at":"2026-07-05T00:43:49.463678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:49.463678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PolyGen: An Autoregressive Generative Model of 3D Meshes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ML"],"primary_cat":"cs.GR","authors_text":"Charlie Nash, Peter W. Battaglia, S. M. Ali Eslami, Yaroslav Ganin","submitted_at":"2020-02-23T17:16:34Z","abstract_excerpt":"Polygon meshes are an efficient representation of 3D geometry, and are of central importance in computer graphics, robotics and games development. Existing learning-based approaches have avoided the challenges of working with 3D meshes, instead using alternative object representations that are more compatible with neural architectures and training approaches. We present an approach which models the mesh directly, predicting mesh vertices and faces sequentially using a Transformer-based architecture. Our model can condition on a range of inputs, including object classes, voxels, and images, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.10880","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/2002.10880/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":"2002.10880","created_at":"2026-07-05T00:43:49.463733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.10880v1","created_at":"2026-07-05T00:43:49.463733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.10880","created_at":"2026-07-05T00:43:49.463733+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4DUCSCYEKMP","created_at":"2026-07-05T00:43:49.463733+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4DUCSCYEKMPP4GL","created_at":"2026-07-05T00:43:49.463733+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4DUCSCY","created_at":"2026-07-05T00:43:49.463733+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19717","citing_title":"Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T4DUCSCYEKMPP4GLT2ZI52AMX2","json":"https://pith.science/pith/T4DUCSCYEKMPP4GLT2ZI52AMX2.json","graph_json":"https://pith.science/api/pith-number/T4DUCSCYEKMPP4GLT2ZI52AMX2/graph.json","events_json":"https://pith.science/api/pith-number/T4DUCSCYEKMPP4GLT2ZI52AMX2/events.json","paper":"https://pith.science/paper/T4DUCSCY"},"agent_actions":{"view_html":"https://pith.science/pith/T4DUCSCYEKMPP4GLT2ZI52AMX2","download_json":"https://pith.science/pith/T4DUCSCYEKMPP4GLT2ZI52AMX2.json","view_paper":"https://pith.science/paper/T4DUCSCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.10880&json=true","fetch_graph":"https://pith.science/api/pith-number/T4DUCSCYEKMPP4GLT2ZI52AMX2/graph.json","fetch_events":"https://pith.science/api/pith-number/T4DUCSCYEKMPP4GLT2ZI52AMX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4DUCSCYEKMPP4GLT2ZI52AMX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4DUCSCYEKMPP4GLT2ZI52AMX2/action/storage_attestation","attest_author":"https://pith.science/pith/T4DUCSCYEKMPP4GLT2ZI52AMX2/action/author_attestation","sign_citation":"https://pith.science/pith/T4DUCSCYEKMPP4GLT2ZI52AMX2/action/citation_signature","submit_replication":"https://pith.science/pith/T4DUCSCYEKMPP4GLT2ZI52AMX2/action/replication_record"}},"created_at":"2026-07-05T00:43:49.463733+00:00","updated_at":"2026-07-05T00:43:49.463733+00:00"}