{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CXQQYTLVMMN4HR4AENDWSXDJ54","short_pith_number":"pith:CXQQYTLV","schema_version":"1.0","canonical_sha256":"15e10c4d75631bc3c7802347695c69ef2496f886b6f4fca8c1613d7161b235be","source":{"kind":"arxiv","id":"2402.12225","version":2},"attestation_state":"computed","paper":{"title":"Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zhao, Chengjie Wang, Simian Luo, Tiejun Huang, Xiangyang Xue, Xuelin Qian, Yanwei Fu, Yinda Zhang, Ying Tai, Yunsheng Wu, Yu Wang, Zhenyu Zhang","submitted_at":"2024-02-19T15:33:09Z","abstract_excerpt":"Auto-regressive models have achieved impressive results in 2D image generation by modeling joint distributions in grid space. In this paper, we extend auto-regressive models to 3D domains, and seek a stronger ability of 3D shape generation by improving auto-regressive models at capacity and scalability simultaneously. Firstly, we leverage an ensemble of publicly available 3D datasets to facilitate the training of large-scale models. It consists of a comprehensive collection of approximately 900,000 objects, with multiple properties of meshes, points, voxels, rendered images, and text captions."},"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":"2402.12225","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-19T15:33:09Z","cross_cats_sorted":[],"title_canon_sha256":"b3ef5e6e2cad06060f6879b4872a582348a05782339663d9880373f12149c8fc","abstract_canon_sha256":"f85eb1871daa8d6ad68d55916305667dfed49ee71ddb08ceab19c5c372cd7402"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:41.121959Z","signature_b64":"gFC3L++asTIy81ZG+rU05d26WY+Hx4i+ThwsymhZr7fF+13IccTqzJMvcpD+pKuC85qzD7AZ790q8OyGi8C3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15e10c4d75631bc3c7802347695c69ef2496f886b6f4fca8c1613d7161b235be","last_reissued_at":"2026-07-05T08:00:41.121485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:41.121485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zhao, Chengjie Wang, Simian Luo, Tiejun Huang, Xiangyang Xue, Xuelin Qian, Yanwei Fu, Yinda Zhang, Ying Tai, Yunsheng Wu, Yu Wang, Zhenyu Zhang","submitted_at":"2024-02-19T15:33:09Z","abstract_excerpt":"Auto-regressive models have achieved impressive results in 2D image generation by modeling joint distributions in grid space. In this paper, we extend auto-regressive models to 3D domains, and seek a stronger ability of 3D shape generation by improving auto-regressive models at capacity and scalability simultaneously. Firstly, we leverage an ensemble of publicly available 3D datasets to facilitate the training of large-scale models. It consists of a comprehensive collection of approximately 900,000 objects, with multiple properties of meshes, points, voxels, rendered images, and text captions."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12225","kind":"arxiv","version":2},"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/2402.12225/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":"2402.12225","created_at":"2026-07-05T08:00:41.121539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12225v2","created_at":"2026-07-05T08:00:41.121539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12225","created_at":"2026-07-05T08:00:41.121539+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXQQYTLVMMN4","created_at":"2026-07-05T08:00:41.121539+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXQQYTLVMMN4HR4A","created_at":"2026-07-05T08:00:41.121539+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXQQYTLV","created_at":"2026-07-05T08:00:41.121539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.21798","citing_title":"CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CXQQYTLVMMN4HR4AENDWSXDJ54","json":"https://pith.science/pith/CXQQYTLVMMN4HR4AENDWSXDJ54.json","graph_json":"https://pith.science/api/pith-number/CXQQYTLVMMN4HR4AENDWSXDJ54/graph.json","events_json":"https://pith.science/api/pith-number/CXQQYTLVMMN4HR4AENDWSXDJ54/events.json","paper":"https://pith.science/paper/CXQQYTLV"},"agent_actions":{"view_html":"https://pith.science/pith/CXQQYTLVMMN4HR4AENDWSXDJ54","download_json":"https://pith.science/pith/CXQQYTLVMMN4HR4AENDWSXDJ54.json","view_paper":"https://pith.science/paper/CXQQYTLV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12225&json=true","fetch_graph":"https://pith.science/api/pith-number/CXQQYTLVMMN4HR4AENDWSXDJ54/graph.json","fetch_events":"https://pith.science/api/pith-number/CXQQYTLVMMN4HR4AENDWSXDJ54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXQQYTLVMMN4HR4AENDWSXDJ54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXQQYTLVMMN4HR4AENDWSXDJ54/action/storage_attestation","attest_author":"https://pith.science/pith/CXQQYTLVMMN4HR4AENDWSXDJ54/action/author_attestation","sign_citation":"https://pith.science/pith/CXQQYTLVMMN4HR4AENDWSXDJ54/action/citation_signature","submit_replication":"https://pith.science/pith/CXQQYTLVMMN4HR4AENDWSXDJ54/action/replication_record"}},"created_at":"2026-07-05T08:00:41.121539+00:00","updated_at":"2026-07-05T08:00:41.121539+00:00"}