{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VSCVYL5J3XSXL6G3FIPZK4H4EE","short_pith_number":"pith:VSCVYL5J","schema_version":"1.0","canonical_sha256":"ac855c2fa9dde575f8db2a1f9570fc212277ca8026727ed5824051a2cb87e142","source":{"kind":"arxiv","id":"2305.11487","version":2},"attestation_state":"computed","paper":{"title":"PointGPT: Auto-regressively Generative Pre-training from Point Clouds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangyan Chen, Kai Yu, Li Yuan, Meiling Wang, Yi Yang, Yufeng Yue","submitted_at":"2023-05-19T07:39:04Z","abstract_excerpt":"Large language models (LLMs) based on the generative pre-training transformer (GPT) have demonstrated remarkable effectiveness across a diverse range of downstream tasks. Inspired by the advancements of the GPT, we present PointGPT, a novel approach that extends the concept of GPT to point clouds, addressing the challenges associated with disorder properties, low information density, and task gaps. Specifically, a point cloud auto-regressive generation task is proposed to pre-train transformer models. Our method partitions the input point cloud into multiple point patches and arranges them in "},"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":"2305.11487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-19T07:39:04Z","cross_cats_sorted":[],"title_canon_sha256":"c5400440f29fe13797a9e7f9eb1d896edf66431f9755cc9f2b1c18bc6a380f63","abstract_canon_sha256":"8c7c636b099ed6ece6c27e1310c39430816771475e5e079c5fb54be25f484442"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:50.903742Z","signature_b64":"boH4vB+dFzq7NWCoRsmlP4ccriAzYukfQW4C2uUMkkwzBMWV80YqAydcL7b8p9iRFxCYXJfvAmNCVhw46QhrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac855c2fa9dde575f8db2a1f9570fc212277ca8026727ed5824051a2cb87e142","last_reissued_at":"2026-07-05T06:12:50.903310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:50.903310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PointGPT: Auto-regressively Generative Pre-training from Point Clouds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangyan Chen, Kai Yu, Li Yuan, Meiling Wang, Yi Yang, Yufeng Yue","submitted_at":"2023-05-19T07:39:04Z","abstract_excerpt":"Large language models (LLMs) based on the generative pre-training transformer (GPT) have demonstrated remarkable effectiveness across a diverse range of downstream tasks. Inspired by the advancements of the GPT, we present PointGPT, a novel approach that extends the concept of GPT to point clouds, addressing the challenges associated with disorder properties, low information density, and task gaps. Specifically, a point cloud auto-regressive generation task is proposed to pre-train transformer models. Our method partitions the input point cloud into multiple point patches and arranges them in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11487","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/2305.11487/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":"2305.11487","created_at":"2026-07-05T06:12:50.903376+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11487v2","created_at":"2026-07-05T06:12:50.903376+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11487","created_at":"2026-07-05T06:12:50.903376+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSCVYL5J3XSX","created_at":"2026-07-05T06:12:50.903376+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSCVYL5J3XSXL6G3","created_at":"2026-07-05T06:12:50.903376+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSCVYL5J","created_at":"2026-07-05T06:12:50.903376+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23830","citing_title":"Deciphering Fingerprints of 3D Molecular Surfaces for Accurate Epitope Prediction","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VSCVYL5J3XSXL6G3FIPZK4H4EE","json":"https://pith.science/pith/VSCVYL5J3XSXL6G3FIPZK4H4EE.json","graph_json":"https://pith.science/api/pith-number/VSCVYL5J3XSXL6G3FIPZK4H4EE/graph.json","events_json":"https://pith.science/api/pith-number/VSCVYL5J3XSXL6G3FIPZK4H4EE/events.json","paper":"https://pith.science/paper/VSCVYL5J"},"agent_actions":{"view_html":"https://pith.science/pith/VSCVYL5J3XSXL6G3FIPZK4H4EE","download_json":"https://pith.science/pith/VSCVYL5J3XSXL6G3FIPZK4H4EE.json","view_paper":"https://pith.science/paper/VSCVYL5J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11487&json=true","fetch_graph":"https://pith.science/api/pith-number/VSCVYL5J3XSXL6G3FIPZK4H4EE/graph.json","fetch_events":"https://pith.science/api/pith-number/VSCVYL5J3XSXL6G3FIPZK4H4EE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSCVYL5J3XSXL6G3FIPZK4H4EE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSCVYL5J3XSXL6G3FIPZK4H4EE/action/storage_attestation","attest_author":"https://pith.science/pith/VSCVYL5J3XSXL6G3FIPZK4H4EE/action/author_attestation","sign_citation":"https://pith.science/pith/VSCVYL5J3XSXL6G3FIPZK4H4EE/action/citation_signature","submit_replication":"https://pith.science/pith/VSCVYL5J3XSXL6G3FIPZK4H4EE/action/replication_record"}},"created_at":"2026-07-05T06:12:50.903376+00:00","updated_at":"2026-07-05T06:12:50.903376+00:00"}