{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4OL6D7GABMWRJBCR2OCLIVX337","short_pith_number":"pith:4OL6D7GA","schema_version":"1.0","canonical_sha256":"e397e1fcc00b2d148451d384b456fbdfd96968e80242e5e4e71679cbfbac64a0","source":{"kind":"arxiv","id":"2409.18313","version":5},"attestation_state":"computed","paper":{"title":"Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Aarav Bajaj, Kedi Xu, Matthew Johnson-Roberson, Pengliang Ji, Quanting Xie, Ruslan Salakhutdinov, So Yeon Min, Tianyi Zhang, Yonatan Bisk, Yue Yang","submitted_at":"2024-09-26T21:44:11Z","abstract_excerpt":"There is no limit to how much a robot might explore and learn, but all of that knowledge needs to be searchable and actionable. Within language research, retrieval augmented generation (RAG) has become the workhorse of large-scale non-parametric knowledge; however, existing techniques do not directly transfer to the embodied domain, which is multimodal, where data is highly correlated, and perception requires abstraction. To address these challenges, we introduce Embodied-RAG, a framework that enhances the foundational model of an embodied agent with a non-parametric memory system capable of a"},"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":"2409.18313","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-26T21:44:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"44879dec2d83133be88a9c21690f53cbd8c7740aedcf31fd2fc1f1551d2782c6","abstract_canon_sha256":"a3e1d2a9cc1d25be8aa6ea8880f829cae0007687e3fd63743a4aff30a3e8f9d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:52.563125Z","signature_b64":"0xFiCvS8ZQEZEez8aUoWX2sppalUibe6A1wpfvnnOKKwa1j5dkBlsaA5OwL9MGjnzQlDXd9Y3UgqCUxfUalTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e397e1fcc00b2d148451d384b456fbdfd96968e80242e5e4e71679cbfbac64a0","last_reissued_at":"2026-07-05T10:02:52.562561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:52.562561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Aarav Bajaj, Kedi Xu, Matthew Johnson-Roberson, Pengliang Ji, Quanting Xie, Ruslan Salakhutdinov, So Yeon Min, Tianyi Zhang, Yonatan Bisk, Yue Yang","submitted_at":"2024-09-26T21:44:11Z","abstract_excerpt":"There is no limit to how much a robot might explore and learn, but all of that knowledge needs to be searchable and actionable. Within language research, retrieval augmented generation (RAG) has become the workhorse of large-scale non-parametric knowledge; however, existing techniques do not directly transfer to the embodied domain, which is multimodal, where data is highly correlated, and perception requires abstraction. To address these challenges, we introduce Embodied-RAG, a framework that enhances the foundational model of an embodied agent with a non-parametric memory system capable of a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18313","kind":"arxiv","version":5},"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/2409.18313/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":"2409.18313","created_at":"2026-07-05T10:02:52.562633+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18313v5","created_at":"2026-07-05T10:02:52.562633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18313","created_at":"2026-07-05T10:02:52.562633+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OL6D7GABMWR","created_at":"2026-07-05T10:02:52.562633+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OL6D7GABMWRJBCR","created_at":"2026-07-05T10:02:52.562633+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OL6D7GA","created_at":"2026-07-05T10:02:52.562633+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25497","citing_title":"SAGE-Nav: Leveraging LLM Planning and Alignment Fusion for Hierarchical Scene Graph-Guided Navigation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19383","citing_title":"3D Scene Graphs: Open Challenges and Future Directions","ref_index":162,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08277","citing_title":"Remember with Confidence: Uncertainty Quantification for Spatio-temporal Memory with Probabilistic Guarantees","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03787","citing_title":"Worth Remembering: Surprise-Gated Robot Episodic Memory","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27826","citing_title":"NormAct: A Benchmark for Hidden Social Norm Compliance in Embodied Planning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28397","citing_title":"CLOSER-VLN: Closed-Loop Self-Verified Retrieval-Augmented Reasoning for Aerial Vision-Language Navigation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22671","citing_title":"From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25371","citing_title":"FOUND-IT: Foundation-model-first Task-driven 3D Scene Graphs with Granularity on Demand","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25646","citing_title":"G-DRAGON: Geospatial Reasoning and Dynamic Planning for Retrieval-Augmented Outdoor Navigation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27762","citing_title":"PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22671","citing_title":"From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2601.17622","citing_title":"Memento: Towards Proactive Visualization of Everyday Memories with Personal Wearable AR Assistant","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10993","citing_title":"ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16482","citing_title":"A Survey of Spatial Memory Representations for Efficient Robot Navigation","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01700","citing_title":"TrajRAG: Retrieving Geometric-Semantic Experience for Zero-Shot Object Navigation","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4OL6D7GABMWRJBCR2OCLIVX337","json":"https://pith.science/pith/4OL6D7GABMWRJBCR2OCLIVX337.json","graph_json":"https://pith.science/api/pith-number/4OL6D7GABMWRJBCR2OCLIVX337/graph.json","events_json":"https://pith.science/api/pith-number/4OL6D7GABMWRJBCR2OCLIVX337/events.json","paper":"https://pith.science/paper/4OL6D7GA"},"agent_actions":{"view_html":"https://pith.science/pith/4OL6D7GABMWRJBCR2OCLIVX337","download_json":"https://pith.science/pith/4OL6D7GABMWRJBCR2OCLIVX337.json","view_paper":"https://pith.science/paper/4OL6D7GA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18313&json=true","fetch_graph":"https://pith.science/api/pith-number/4OL6D7GABMWRJBCR2OCLIVX337/graph.json","fetch_events":"https://pith.science/api/pith-number/4OL6D7GABMWRJBCR2OCLIVX337/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OL6D7GABMWRJBCR2OCLIVX337/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OL6D7GABMWRJBCR2OCLIVX337/action/storage_attestation","attest_author":"https://pith.science/pith/4OL6D7GABMWRJBCR2OCLIVX337/action/author_attestation","sign_citation":"https://pith.science/pith/4OL6D7GABMWRJBCR2OCLIVX337/action/citation_signature","submit_replication":"https://pith.science/pith/4OL6D7GABMWRJBCR2OCLIVX337/action/replication_record"}},"created_at":"2026-07-05T10:02:52.562633+00:00","updated_at":"2026-07-05T10:02:52.562633+00:00"}