{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VNN2A57YRUIMTGFJA763DIVX2R","short_pith_number":"pith:VNN2A57Y","schema_version":"1.0","canonical_sha256":"ab5ba077f88d10c998a907fdb1a2b7d464b827003e15063976e7fcf1dab2de8c","source":{"kind":"arxiv","id":"2504.09975","version":2},"attestation_state":"computed","paper":{"title":"OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Baoquan Chen, Chuan-Zhi Zhou, Peng-Shuai Wang, Rui-Huan Wang, Si-Tong Wei","submitted_at":"2025-04-14T08:31:26Z","abstract_excerpt":"Autoregressive models have achieved remarkable success across various domains, yet their performance in 3D shape generation lags significantly behind that of diffusion models. In this paper, we introduce OctGPT, a novel multiscale autoregressive model for 3D shape generation that dramatically improves the efficiency and performance of prior 3D autoregressive approaches, while rivaling or surpassing state-of-the-art diffusion models. Our method employs a serialized octree representation to efficiently capture the hierarchical and spatial structures of 3D shapes. Coarse geometry is encoded via o"},"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":"2504.09975","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2025-04-14T08:31:26Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7876d144c0dbe3c8a79603b3822f3f8694a61e5a42653567fad6325713776737","abstract_canon_sha256":"2a0b93c660c292b7d43390a5aad63b40979cee32fb4c31fc68e5ab0e8a987b5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:18.057507Z","signature_b64":"ZO1A1HjGQDXgxJpVqTu/3Y2GP7itgy9pKco4MZ00ArGYZWIPlyApUMOusOWVgquPElkqZE4Aibiwb5PLzJLcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab5ba077f88d10c998a907fdb1a2b7d464b827003e15063976e7fcf1dab2de8c","last_reissued_at":"2026-07-05T10:49:18.057011Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:18.057011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Baoquan Chen, Chuan-Zhi Zhou, Peng-Shuai Wang, Rui-Huan Wang, Si-Tong Wei","submitted_at":"2025-04-14T08:31:26Z","abstract_excerpt":"Autoregressive models have achieved remarkable success across various domains, yet their performance in 3D shape generation lags significantly behind that of diffusion models. In this paper, we introduce OctGPT, a novel multiscale autoregressive model for 3D shape generation that dramatically improves the efficiency and performance of prior 3D autoregressive approaches, while rivaling or surpassing state-of-the-art diffusion models. Our method employs a serialized octree representation to efficiently capture the hierarchical and spatial structures of 3D shapes. Coarse geometry is encoded via o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09975","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/2504.09975/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":"2504.09975","created_at":"2026-07-05T10:49:18.057070+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.09975v2","created_at":"2026-07-05T10:49:18.057070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09975","created_at":"2026-07-05T10:49:18.057070+00:00"},{"alias_kind":"pith_short_12","alias_value":"VNN2A57YRUIM","created_at":"2026-07-05T10:49:18.057070+00:00"},{"alias_kind":"pith_short_16","alias_value":"VNN2A57YRUIMTGFJ","created_at":"2026-07-05T10:49:18.057070+00:00"},{"alias_kind":"pith_short_8","alias_value":"VNN2A57Y","created_at":"2026-07-05T10:49:18.057070+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.12635","citing_title":"MVPainter: Accurate and Detailed 3D Texture Generation via Multi-View Diffusion with Geometric Control","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VNN2A57YRUIMTGFJA763DIVX2R","json":"https://pith.science/pith/VNN2A57YRUIMTGFJA763DIVX2R.json","graph_json":"https://pith.science/api/pith-number/VNN2A57YRUIMTGFJA763DIVX2R/graph.json","events_json":"https://pith.science/api/pith-number/VNN2A57YRUIMTGFJA763DIVX2R/events.json","paper":"https://pith.science/paper/VNN2A57Y"},"agent_actions":{"view_html":"https://pith.science/pith/VNN2A57YRUIMTGFJA763DIVX2R","download_json":"https://pith.science/pith/VNN2A57YRUIMTGFJA763DIVX2R.json","view_paper":"https://pith.science/paper/VNN2A57Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.09975&json=true","fetch_graph":"https://pith.science/api/pith-number/VNN2A57YRUIMTGFJA763DIVX2R/graph.json","fetch_events":"https://pith.science/api/pith-number/VNN2A57YRUIMTGFJA763DIVX2R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VNN2A57YRUIMTGFJA763DIVX2R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VNN2A57YRUIMTGFJA763DIVX2R/action/storage_attestation","attest_author":"https://pith.science/pith/VNN2A57YRUIMTGFJA763DIVX2R/action/author_attestation","sign_citation":"https://pith.science/pith/VNN2A57YRUIMTGFJA763DIVX2R/action/citation_signature","submit_replication":"https://pith.science/pith/VNN2A57YRUIMTGFJA763DIVX2R/action/replication_record"}},"created_at":"2026-07-05T10:49:18.057070+00:00","updated_at":"2026-07-05T10:49:18.057070+00:00"}