{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FEODEPQKCZ6PH2CWHAEFWHF5IB","short_pith_number":"pith:FEODEPQK","schema_version":"1.0","canonical_sha256":"291c323e0a167cf3e85638085b1cbd405b8414c4226d4ee85ddaf559bcd95d67","source":{"kind":"arxiv","id":"2410.03878","version":2},"attestation_state":"computed","paper":{"title":"SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lifu Huang, Parisa Kordjamshidi, Ying Shen, Yue Zhang, Zhiyang Xu","submitted_at":"2024-10-04T19:22:20Z","abstract_excerpt":"Integrating the 3D world into large language models (3D-based LLMs) has been a promising research direction for 3D scene understanding. However, current 3D-based LLMs fall short in situated understanding due to two key limitations: 1) existing 3D datasets are constructed from a global perspective of the 3D scenes and lack situated context. 2) the architectures of existing 3D-based LLMs lack explicit alignment between the spatial representations of 3D scenes and natural language, limiting their performance in tasks requiring precise spatial reasoning. We address these issues by introducing a sc"},"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":"2410.03878","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T19:22:20Z","cross_cats_sorted":[],"title_canon_sha256":"35f26a0936173cf6821a47e01b4278aab63142333d3f0395cf78c0ef4ee2daf0","abstract_canon_sha256":"bf6d3f518b45886fe5d83bcf53088c249b8e9e0811f7880e734f39ae9b305598"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:06.158661Z","signature_b64":"8/0ZrH85S3HKsM5wLsdO1LxtalmJeyFZAz6WFDuGh6Zn0irJ/2z1ySyugDIY950wKJnaD2cZ1bdHDX4HFZLqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"291c323e0a167cf3e85638085b1cbd405b8414c4226d4ee85ddaf559bcd95d67","last_reissued_at":"2026-07-05T10:22:06.158148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:06.158148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lifu Huang, Parisa Kordjamshidi, Ying Shen, Yue Zhang, Zhiyang Xu","submitted_at":"2024-10-04T19:22:20Z","abstract_excerpt":"Integrating the 3D world into large language models (3D-based LLMs) has been a promising research direction for 3D scene understanding. However, current 3D-based LLMs fall short in situated understanding due to two key limitations: 1) existing 3D datasets are constructed from a global perspective of the 3D scenes and lack situated context. 2) the architectures of existing 3D-based LLMs lack explicit alignment between the spatial representations of 3D scenes and natural language, limiting their performance in tasks requiring precise spatial reasoning. We address these issues by introducing a sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03878","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/2410.03878/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":"2410.03878","created_at":"2026-07-05T10:22:06.158212+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03878v2","created_at":"2026-07-05T10:22:06.158212+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03878","created_at":"2026-07-05T10:22:06.158212+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEODEPQKCZ6P","created_at":"2026-07-05T10:22:06.158212+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEODEPQKCZ6PH2CW","created_at":"2026-07-05T10:22:06.158212+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEODEPQK","created_at":"2026-07-05T10:22:06.158212+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01784","citing_title":"SpaceEra++: A Unified Framework Towards 3D Spatial Reasoning in Video","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FEODEPQKCZ6PH2CWHAEFWHF5IB","json":"https://pith.science/pith/FEODEPQKCZ6PH2CWHAEFWHF5IB.json","graph_json":"https://pith.science/api/pith-number/FEODEPQKCZ6PH2CWHAEFWHF5IB/graph.json","events_json":"https://pith.science/api/pith-number/FEODEPQKCZ6PH2CWHAEFWHF5IB/events.json","paper":"https://pith.science/paper/FEODEPQK"},"agent_actions":{"view_html":"https://pith.science/pith/FEODEPQKCZ6PH2CWHAEFWHF5IB","download_json":"https://pith.science/pith/FEODEPQKCZ6PH2CWHAEFWHF5IB.json","view_paper":"https://pith.science/paper/FEODEPQK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03878&json=true","fetch_graph":"https://pith.science/api/pith-number/FEODEPQKCZ6PH2CWHAEFWHF5IB/graph.json","fetch_events":"https://pith.science/api/pith-number/FEODEPQKCZ6PH2CWHAEFWHF5IB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEODEPQKCZ6PH2CWHAEFWHF5IB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEODEPQKCZ6PH2CWHAEFWHF5IB/action/storage_attestation","attest_author":"https://pith.science/pith/FEODEPQKCZ6PH2CWHAEFWHF5IB/action/author_attestation","sign_citation":"https://pith.science/pith/FEODEPQKCZ6PH2CWHAEFWHF5IB/action/citation_signature","submit_replication":"https://pith.science/pith/FEODEPQKCZ6PH2CWHAEFWHF5IB/action/replication_record"}},"created_at":"2026-07-05T10:22:06.158212+00:00","updated_at":"2026-07-05T10:22:06.158212+00:00"}