{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4MPALBNCHNHRZEKPSRORGCPJQ4","short_pith_number":"pith:4MPALBNC","schema_version":"1.0","canonical_sha256":"e31e0585a23b4f1c914f945d1309e98711c46fb016918a289aff6bb8aab33cd8","source":{"kind":"arxiv","id":"2307.12981","version":1},"attestation_state":"computed","paper":{"title":"3D-LLM: Injecting the 3D World into Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Chuang Gan, Haoyu Zhen, Peihao Chen, Shuhong Zheng, Yilun Du, Yining Hong, Zhenfang Chen","submitted_at":"2023-07-24T17:59:02Z","abstract_excerpt":"Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense caption"},"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":"2307.12981","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-24T17:59:02Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"bb85b74b1cea07baf700d6df20cedbd946d6c47824f815e882197b42d0884b6a","abstract_canon_sha256":"2385e61a0580e2f954cde8ec5023ca1c8dbadc8f471c0e807f5e73b61a5e5bac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:01.027730Z","signature_b64":"PtEZiKDtpj+6JHzKBeJ+2RLeDB/j5UCTjn+xlyCXwvZKptOZpXTMsJUg/IW1cvIfd5TTyG9VCdPub6wHoqXKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e31e0585a23b4f1c914f945d1309e98711c46fb016918a289aff6bb8aab33cd8","last_reissued_at":"2026-07-05T06:34:01.027293Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:01.027293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D-LLM: Injecting the 3D World into Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Chuang Gan, Haoyu Zhen, Peihao Chen, Shuhong Zheng, Yilun Du, Yining Hong, Zhenfang Chen","submitted_at":"2023-07-24T17:59:02Z","abstract_excerpt":"Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense caption"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12981","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/2307.12981/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":"2307.12981","created_at":"2026-07-05T06:34:01.027363+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.12981v1","created_at":"2026-07-05T06:34:01.027363+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12981","created_at":"2026-07-05T06:34:01.027363+00:00"},{"alias_kind":"pith_short_12","alias_value":"4MPALBNCHNHR","created_at":"2026-07-05T06:34:01.027363+00:00"},{"alias_kind":"pith_short_16","alias_value":"4MPALBNCHNHRZEKP","created_at":"2026-07-05T06:34:01.027363+00:00"},{"alias_kind":"pith_short_8","alias_value":"4MPALBNC","created_at":"2026-07-05T06:34:01.027363+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"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":18,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02742","citing_title":"Consistent Yet Wrong: Evidence Insensitivity in Spatial Vision-Language Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21798","citing_title":"CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2511.10946","citing_title":"Abstract 3D Perception for Spatial Intelligence in Vision-Language Models","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2311.07575","citing_title":"SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2603.08592","citing_title":"Boosting MLLM Spatial Reasoning with Geometrically Referenced 3D Scene Representations","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27507","citing_title":"Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2403.09631","citing_title":"3D-VLA: A 3D Vision-Language-Action Generative World Model","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4MPALBNCHNHRZEKPSRORGCPJQ4","json":"https://pith.science/pith/4MPALBNCHNHRZEKPSRORGCPJQ4.json","graph_json":"https://pith.science/api/pith-number/4MPALBNCHNHRZEKPSRORGCPJQ4/graph.json","events_json":"https://pith.science/api/pith-number/4MPALBNCHNHRZEKPSRORGCPJQ4/events.json","paper":"https://pith.science/paper/4MPALBNC"},"agent_actions":{"view_html":"https://pith.science/pith/4MPALBNCHNHRZEKPSRORGCPJQ4","download_json":"https://pith.science/pith/4MPALBNCHNHRZEKPSRORGCPJQ4.json","view_paper":"https://pith.science/paper/4MPALBNC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.12981&json=true","fetch_graph":"https://pith.science/api/pith-number/4MPALBNCHNHRZEKPSRORGCPJQ4/graph.json","fetch_events":"https://pith.science/api/pith-number/4MPALBNCHNHRZEKPSRORGCPJQ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4MPALBNCHNHRZEKPSRORGCPJQ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4MPALBNCHNHRZEKPSRORGCPJQ4/action/storage_attestation","attest_author":"https://pith.science/pith/4MPALBNCHNHRZEKPSRORGCPJQ4/action/author_attestation","sign_citation":"https://pith.science/pith/4MPALBNCHNHRZEKPSRORGCPJQ4/action/citation_signature","submit_replication":"https://pith.science/pith/4MPALBNCHNHRZEKPSRORGCPJQ4/action/replication_record"}},"created_at":"2026-07-05T06:34:01.027363+00:00","updated_at":"2026-07-05T06:34:01.027363+00:00"}