{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ETLHFF36BXMHOE2W6UDRH363TT","short_pith_number":"pith:ETLHFF36","schema_version":"1.0","canonical_sha256":"24d672977e0dd8771356f50713efdb9ce2e9252a75f2ec451eaf7456543ec187","source":{"kind":"arxiv","id":"2410.23968","version":1},"attestation_state":"computed","paper":{"title":"EmbodiedRAG: Dynamic 3D Scene Graph Retrieval for Efficient and Scalable Robot Task Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Aurora Schmidt, Bethany Kemp, Corban Rivera, Grayson Byrd, Meghan Booker","submitted_at":"2024-10-31T14:22:20Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) have helped facilitate exciting progress for robotic planning in real, open-world environments. 3D scene graphs (3DSGs) offer a promising environment representation for grounding such LLM-based planners as they are compact and semantically rich. However, as the robot's environment scales (e.g., number of entities tracked) and the complexity of scene graph information increases (e.g., maintaining more attributes), providing the 3DSG as-is to an LLM-based planner quickly becomes infeasible due to input token count limits and attentional biases pres"},"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":"2410.23968","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-31T14:22:20Z","cross_cats_sorted":[],"title_canon_sha256":"9497a92b3bebda99ebc7b9e13e748e6b789cbd78904a3b7627833d620b793072","abstract_canon_sha256":"dd492ad3e1faa86ebe1d03fca2a85e64fa74c399ccbecff043b94688f5262a26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:17.125810Z","signature_b64":"QbLMYjRC3A8dgpOuD++kG+iIaJN661L4+Qyb7OrRRlPsRtjTbRP+Y1XwieICcQpuXhc7QsL8awqpJNoGowuRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24d672977e0dd8771356f50713efdb9ce2e9252a75f2ec451eaf7456543ec187","last_reissued_at":"2026-07-05T09:29:17.125274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:17.125274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EmbodiedRAG: Dynamic 3D Scene Graph Retrieval for Efficient and Scalable Robot Task Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Aurora Schmidt, Bethany Kemp, Corban Rivera, Grayson Byrd, Meghan Booker","submitted_at":"2024-10-31T14:22:20Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) have helped facilitate exciting progress for robotic planning in real, open-world environments. 3D scene graphs (3DSGs) offer a promising environment representation for grounding such LLM-based planners as they are compact and semantically rich. However, as the robot's environment scales (e.g., number of entities tracked) and the complexity of scene graph information increases (e.g., maintaining more attributes), providing the 3DSG as-is to an LLM-based planner quickly becomes infeasible due to input token count limits and attentional biases pres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23968","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/2410.23968/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":"2410.23968","created_at":"2026-07-05T09:29:17.125346+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23968v1","created_at":"2026-07-05T09:29:17.125346+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23968","created_at":"2026-07-05T09:29:17.125346+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETLHFF36BXMH","created_at":"2026-07-05T09:29:17.125346+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETLHFF36BXMHOE2W","created_at":"2026-07-05T09:29:17.125346+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETLHFF36","created_at":"2026-07-05T09:29:17.125346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24068","citing_title":"ObsGraph: Hierarchical Observation Representation for Embodied Reasoning and Exploration","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00889","citing_title":"DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03374","citing_title":"eMEM: A Hybrid Spatio-Temporal Memory System For Embodied Agents","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18109","citing_title":"TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01700","citing_title":"TrajRAG: Retrieving Geometric-Semantic Experience for Zero-Shot Object Navigation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07774","citing_title":"RoboAgent: Chaining Basic Capabilities for Embodied Task Planning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17190","citing_title":"LookasideVLN: Direction-Aware Aerial Vision-and-Language Navigation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ETLHFF36BXMHOE2W6UDRH363TT","json":"https://pith.science/pith/ETLHFF36BXMHOE2W6UDRH363TT.json","graph_json":"https://pith.science/api/pith-number/ETLHFF36BXMHOE2W6UDRH363TT/graph.json","events_json":"https://pith.science/api/pith-number/ETLHFF36BXMHOE2W6UDRH363TT/events.json","paper":"https://pith.science/paper/ETLHFF36"},"agent_actions":{"view_html":"https://pith.science/pith/ETLHFF36BXMHOE2W6UDRH363TT","download_json":"https://pith.science/pith/ETLHFF36BXMHOE2W6UDRH363TT.json","view_paper":"https://pith.science/paper/ETLHFF36","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23968&json=true","fetch_graph":"https://pith.science/api/pith-number/ETLHFF36BXMHOE2W6UDRH363TT/graph.json","fetch_events":"https://pith.science/api/pith-number/ETLHFF36BXMHOE2W6UDRH363TT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETLHFF36BXMHOE2W6UDRH363TT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETLHFF36BXMHOE2W6UDRH363TT/action/storage_attestation","attest_author":"https://pith.science/pith/ETLHFF36BXMHOE2W6UDRH363TT/action/author_attestation","sign_citation":"https://pith.science/pith/ETLHFF36BXMHOE2W6UDRH363TT/action/citation_signature","submit_replication":"https://pith.science/pith/ETLHFF36BXMHOE2W6UDRH363TT/action/replication_record"}},"created_at":"2026-07-05T09:29:17.125346+00:00","updated_at":"2026-07-05T09:29:17.125346+00:00"}