{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QVV5KNQE7SLJZI4RWXBAESXSPH","short_pith_number":"pith:QVV5KNQE","schema_version":"1.0","canonical_sha256":"856bd53604fc969ca391b5c2024af279c95bb63e5be2b2edbba002d04b13ac28","source":{"kind":"arxiv","id":"2307.06135","version":2},"attestation_state":"computed","paper":{"title":"SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Ian Reid, Jad Abou-Chakra, Jesse Haviland, Krishan Rana, Niko Suenderhauf, Sourav Garg","submitted_at":"2023-07-12T12:37:55Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive results in developing generalist planning agents for diverse tasks. However, grounding these plans in expansive, multi-floor, and multi-room environments presents a significant challenge for robotics. We introduce SayPlan, a scalable approach to LLM-based, large-scale task planning for robotics using 3D scene graph (3DSG) representations. To ensure the scalability of our approach, we: (1) exploit the hierarchical nature of 3DSGs to allow LLMs to conduct a 'semantic search' for task-relevant subgraphs from a smaller, collapsed representa"},"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":"2307.06135","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-07-12T12:37:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c1504e0ad2fe2d8e0318ceea148848e70d0deb734cc20f02a2c55914521f0354","abstract_canon_sha256":"4def4f3751c24611bf5c99fb76c0f297964b995b15b6e4c89cb2945382b18f0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:04.822290Z","signature_b64":"1EnjcmtEsP4cJjMTVC7kDvKdoxYzMgbkQKv4JwcQMnySmsYUt8PxCWCnLszVSweOgjyQEllJ4T9iV0Kt3ZDtCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"856bd53604fc969ca391b5c2024af279c95bb63e5be2b2edbba002d04b13ac28","last_reissued_at":"2026-07-05T06:55:04.821858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:04.821858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Ian Reid, Jad Abou-Chakra, Jesse Haviland, Krishan Rana, Niko Suenderhauf, Sourav Garg","submitted_at":"2023-07-12T12:37:55Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive results in developing generalist planning agents for diverse tasks. However, grounding these plans in expansive, multi-floor, and multi-room environments presents a significant challenge for robotics. We introduce SayPlan, a scalable approach to LLM-based, large-scale task planning for robotics using 3D scene graph (3DSG) representations. To ensure the scalability of our approach, we: (1) exploit the hierarchical nature of 3DSGs to allow LLMs to conduct a 'semantic search' for task-relevant subgraphs from a smaller, collapsed representa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06135","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/2307.06135/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":"2307.06135","created_at":"2026-07-05T06:55:04.821912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.06135v2","created_at":"2026-07-05T06:55:04.821912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06135","created_at":"2026-07-05T06:55:04.821912+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVV5KNQE7SLJ","created_at":"2026-07-05T06:55:04.821912+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVV5KNQE7SLJZI4R","created_at":"2026-07-05T06:55:04.821912+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVV5KNQE","created_at":"2026-07-05T06:55:04.821912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"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":45,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21470","citing_title":"ASCII Art Turns LLMs into VLA Controllers","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08952","citing_title":"AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05621","citing_title":"ANCHOR: Agentic Noise Creation Framework for Human Simulation and Denoising Recommendation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31404","citing_title":"The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spatial Reasoning in Navigation Planning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31260","citing_title":"Plan Right, Then Plan Tight: Symbolic RL for Efficient Embodied Reasoning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25059","citing_title":"VEOcc: Voxel-Centric Online Semantic Occupancy Prediction For Embodied Scene Understanding","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2409.13107","citing_title":"Towards Robust Surgical Automation via Digital Twin Representations from Foundation Models","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14504","citing_title":"When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18109","citing_title":"TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18184","citing_title":"Fixed External Cameras as Common Prior Maps for Active 3D Scene Graph Generation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18197","citing_title":"RGB-only Active 3D Scene Graph Generation for Indoor Mobile Robots","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19420","citing_title":"Beyond Waypoints: Dual-Heatmap Grounding for Cross-Embodiment Semantic Navigation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2511.12676","citing_title":"BridgeEQA: Virtual Embodied Agents for Real Bridge Inspections","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2602.08392","citing_title":"ST-BiBench: Benchmarking Multi-Stream Multimodal Coordination in Bimanual Embodied Tasks for MLLMs","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14504","citing_title":"When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2510.13778","citing_title":"InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2304.11477","citing_title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21924","citing_title":"Long-Horizon Manipulation via Trace-Conditioned VLA Planning","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2309.07864","citing_title":"The Rise and Potential of Large Language Model Based Agents: A Survey","ref_index":261,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07034","citing_title":"KITE: Keyframe-Indexed Tokenized Evidence for VLM-Based Robot Failure Analysis","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QVV5KNQE7SLJZI4RWXBAESXSPH","json":"https://pith.science/pith/QVV5KNQE7SLJZI4RWXBAESXSPH.json","graph_json":"https://pith.science/api/pith-number/QVV5KNQE7SLJZI4RWXBAESXSPH/graph.json","events_json":"https://pith.science/api/pith-number/QVV5KNQE7SLJZI4RWXBAESXSPH/events.json","paper":"https://pith.science/paper/QVV5KNQE"},"agent_actions":{"view_html":"https://pith.science/pith/QVV5KNQE7SLJZI4RWXBAESXSPH","download_json":"https://pith.science/pith/QVV5KNQE7SLJZI4RWXBAESXSPH.json","view_paper":"https://pith.science/paper/QVV5KNQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.06135&json=true","fetch_graph":"https://pith.science/api/pith-number/QVV5KNQE7SLJZI4RWXBAESXSPH/graph.json","fetch_events":"https://pith.science/api/pith-number/QVV5KNQE7SLJZI4RWXBAESXSPH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVV5KNQE7SLJZI4RWXBAESXSPH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVV5KNQE7SLJZI4RWXBAESXSPH/action/storage_attestation","attest_author":"https://pith.science/pith/QVV5KNQE7SLJZI4RWXBAESXSPH/action/author_attestation","sign_citation":"https://pith.science/pith/QVV5KNQE7SLJZI4RWXBAESXSPH/action/citation_signature","submit_replication":"https://pith.science/pith/QVV5KNQE7SLJZI4RWXBAESXSPH/action/replication_record"}},"created_at":"2026-07-05T06:55:04.821912+00:00","updated_at":"2026-07-05T06:55:04.821912+00:00"}