{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EEBBQCOU4EJQ5CS2Y3GY3AMIJ3","short_pith_number":"pith:EEBBQCOU","schema_version":"1.0","canonical_sha256":"21021809d4e1130e8a5ac6cd8d81884efd84d1f6a133ae461d7fe572037e8849","source":{"kind":"arxiv","id":"2402.03327","version":1},"attestation_state":"computed","paper":{"title":"Uni3D-LLM: Unifying Point Cloud Perception, Generation and Editing with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Dingning Liu, Peng Gao, Wanli Ouyang, Xiaoshui Huang, Yongshun Gong, Yuenan Hou, Zhenfei Yin, Zhihui Wang","submitted_at":"2024-01-09T06:20:23Z","abstract_excerpt":"In this paper, we introduce Uni3D-LLM, a unified framework that leverages a Large Language Model (LLM) to integrate tasks of 3D perception, generation, and editing within point cloud scenes. This framework empowers users to effortlessly generate and modify objects at specified locations within a scene, guided by the versatility of natural language descriptions. Uni3D-LLM harnesses the expressive power of natural language to allow for precise command over the generation and editing of 3D objects, thereby significantly enhancing operational flexibility and controllability. By mapping point cloud"},"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":"2402.03327","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-09T06:20:23Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"3f8e14457f875cb017fee186aa5bb1128e61fd2557d1f4c0020b796b705e12f3","abstract_canon_sha256":"95bd4345bac0cb699c75891585548250f1cd37eed9b3bc7bd86c0198c8dab09a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:50.825693Z","signature_b64":"SrS2VWTMp3N5C83x1dSKLfXxnT4Lc7FMRwYSD4mUa0AhDsG9qFu6HvZC1vws3PNXnLNUhdAaBDbRdVIMALONDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21021809d4e1130e8a5ac6cd8d81884efd84d1f6a133ae461d7fe572037e8849","last_reissued_at":"2026-07-05T07:41:50.825164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:50.825164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uni3D-LLM: Unifying Point Cloud Perception, Generation and Editing with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Dingning Liu, Peng Gao, Wanli Ouyang, Xiaoshui Huang, Yongshun Gong, Yuenan Hou, Zhenfei Yin, Zhihui Wang","submitted_at":"2024-01-09T06:20:23Z","abstract_excerpt":"In this paper, we introduce Uni3D-LLM, a unified framework that leverages a Large Language Model (LLM) to integrate tasks of 3D perception, generation, and editing within point cloud scenes. This framework empowers users to effortlessly generate and modify objects at specified locations within a scene, guided by the versatility of natural language descriptions. Uni3D-LLM harnesses the expressive power of natural language to allow for precise command over the generation and editing of 3D objects, thereby significantly enhancing operational flexibility and controllability. By mapping point cloud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03327","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/2402.03327/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":"2402.03327","created_at":"2026-07-05T07:41:50.825223+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03327v1","created_at":"2026-07-05T07:41:50.825223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03327","created_at":"2026-07-05T07:41:50.825223+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEBBQCOU4EJQ","created_at":"2026-07-05T07:41:50.825223+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEBBQCOU4EJQ5CS2","created_at":"2026-07-05T07:41:50.825223+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEBBQCOU","created_at":"2026-07-05T07:41:50.825223+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06565","citing_title":"ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation","ref_index":103,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18039","citing_title":"SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signals","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2603.10963","citing_title":"Pointy - A Lightweight Transformer for Point Cloud Foundation Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08645","citing_title":"3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EEBBQCOU4EJQ5CS2Y3GY3AMIJ3","json":"https://pith.science/pith/EEBBQCOU4EJQ5CS2Y3GY3AMIJ3.json","graph_json":"https://pith.science/api/pith-number/EEBBQCOU4EJQ5CS2Y3GY3AMIJ3/graph.json","events_json":"https://pith.science/api/pith-number/EEBBQCOU4EJQ5CS2Y3GY3AMIJ3/events.json","paper":"https://pith.science/paper/EEBBQCOU"},"agent_actions":{"view_html":"https://pith.science/pith/EEBBQCOU4EJQ5CS2Y3GY3AMIJ3","download_json":"https://pith.science/pith/EEBBQCOU4EJQ5CS2Y3GY3AMIJ3.json","view_paper":"https://pith.science/paper/EEBBQCOU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03327&json=true","fetch_graph":"https://pith.science/api/pith-number/EEBBQCOU4EJQ5CS2Y3GY3AMIJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/EEBBQCOU4EJQ5CS2Y3GY3AMIJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEBBQCOU4EJQ5CS2Y3GY3AMIJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEBBQCOU4EJQ5CS2Y3GY3AMIJ3/action/storage_attestation","attest_author":"https://pith.science/pith/EEBBQCOU4EJQ5CS2Y3GY3AMIJ3/action/author_attestation","sign_citation":"https://pith.science/pith/EEBBQCOU4EJQ5CS2Y3GY3AMIJ3/action/citation_signature","submit_replication":"https://pith.science/pith/EEBBQCOU4EJQ5CS2Y3GY3AMIJ3/action/replication_record"}},"created_at":"2026-07-05T07:41:50.825223+00:00","updated_at":"2026-07-05T07:41:50.825223+00:00"}