{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H5TR6ICCCMZWEAFH3CLLJURWDX","short_pith_number":"pith:H5TR6ICC","schema_version":"1.0","canonical_sha256":"3f671f204213336200a7d896b4d2361dd9d9f5e47ee129ce6892e4d7989ec6d5","source":{"kind":"arxiv","id":"2412.18450","version":3},"attestation_state":"computed","paper":{"title":"3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dmitry Yudin, Tatiana Zemskova","submitted_at":"2024-12-24T14:21:58Z","abstract_excerpt":"A 3D scene graph represents a compact scene model by capturing both the objects present and the semantic relationships between them, making it a promising structure for robotic applications. To effectively interact with users, an embodied intelligent agent should be able to answer a wide range of natural language queries about the surrounding 3D environment. Large Language Models (LLMs) are beneficial solutions for user-robot interaction due to their natural language understanding and reasoning abilities. Recent methods for learning scene representations have shown that adapting these represen"},"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":"2412.18450","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T14:21:58Z","cross_cats_sorted":[],"title_canon_sha256":"b066cf8bf245d1957659d68e8678fe7b70596e484f499bf89a4e2438ea4e3110","abstract_canon_sha256":"51bdf780e0165d8be4efc8185f87ae7abddf9f8d676ba3aa52cb98f58ddb24cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:06.012879Z","signature_b64":"LHUtA4SIkvk0UlKVM4G5u1f07Trz7q//2NSsh6ob527EJbh3vV301tZuNwrB3mjdhxeg1U1v7nLsi4rKtsalDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f671f204213336200a7d896b4d2361dd9d9f5e47ee129ce6892e4d7989ec6d5","last_reissued_at":"2026-07-05T11:49:06.012387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:06.012387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dmitry Yudin, Tatiana Zemskova","submitted_at":"2024-12-24T14:21:58Z","abstract_excerpt":"A 3D scene graph represents a compact scene model by capturing both the objects present and the semantic relationships between them, making it a promising structure for robotic applications. To effectively interact with users, an embodied intelligent agent should be able to answer a wide range of natural language queries about the surrounding 3D environment. Large Language Models (LLMs) are beneficial solutions for user-robot interaction due to their natural language understanding and reasoning abilities. Recent methods for learning scene representations have shown that adapting these represen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18450","kind":"arxiv","version":3},"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/2412.18450/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":"2412.18450","created_at":"2026-07-05T11:49:06.012445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18450v3","created_at":"2026-07-05T11:49:06.012445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18450","created_at":"2026-07-05T11:49:06.012445+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5TR6ICCCMZW","created_at":"2026-07-05T11:49:06.012445+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5TR6ICCCMZWEAFH","created_at":"2026-07-05T11:49:06.012445+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5TR6ICC","created_at":"2026-07-05T11:49:06.012445+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06534","citing_title":"CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H5TR6ICCCMZWEAFH3CLLJURWDX","json":"https://pith.science/pith/H5TR6ICCCMZWEAFH3CLLJURWDX.json","graph_json":"https://pith.science/api/pith-number/H5TR6ICCCMZWEAFH3CLLJURWDX/graph.json","events_json":"https://pith.science/api/pith-number/H5TR6ICCCMZWEAFH3CLLJURWDX/events.json","paper":"https://pith.science/paper/H5TR6ICC"},"agent_actions":{"view_html":"https://pith.science/pith/H5TR6ICCCMZWEAFH3CLLJURWDX","download_json":"https://pith.science/pith/H5TR6ICCCMZWEAFH3CLLJURWDX.json","view_paper":"https://pith.science/paper/H5TR6ICC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18450&json=true","fetch_graph":"https://pith.science/api/pith-number/H5TR6ICCCMZWEAFH3CLLJURWDX/graph.json","fetch_events":"https://pith.science/api/pith-number/H5TR6ICCCMZWEAFH3CLLJURWDX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5TR6ICCCMZWEAFH3CLLJURWDX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5TR6ICCCMZWEAFH3CLLJURWDX/action/storage_attestation","attest_author":"https://pith.science/pith/H5TR6ICCCMZWEAFH3CLLJURWDX/action/author_attestation","sign_citation":"https://pith.science/pith/H5TR6ICCCMZWEAFH3CLLJURWDX/action/citation_signature","submit_replication":"https://pith.science/pith/H5TR6ICCCMZWEAFH3CLLJURWDX/action/replication_record"}},"created_at":"2026-07-05T11:49:06.012445+00:00","updated_at":"2026-07-05T11:49:06.012445+00:00"}