{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UTLOOWSPRET6XIR2P2Y5XIX7PA","short_pith_number":"pith:UTLOOWSP","schema_version":"1.0","canonical_sha256":"a4d6e75a4f8927eba23a7eb1dba2ff780377a0c1691aec3354ca99f5b82deabe","source":{"kind":"arxiv","id":"2210.05714","version":4},"attestation_state":"computed","paper":{"title":"Visual Language Maps for Robot Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Andy Zeng, Chenguang Huang, Oier Mees, Wolfram Burgard","submitted_at":"2022-10-11T18:13:20Z","abstract_excerpt":"Grounding language to the visual observations of a navigating agent can be performed using off-the-shelf visual-language models pretrained on Internet-scale data (e.g., image captions). While this is useful for matching images to natural language descriptions of object goals, it remains disjoint from the process of mapping the environment, so that it lacks the spatial precision of classic geometric maps. To address this problem, we propose VLMaps, a spatial map representation that directly fuses pretrained visual-language features with a 3D reconstruction of the physical world. VLMaps can be 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":"2210.05714","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-10-11T18:13:20Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"24965fb634288c45570a0dc183d805433eb70c22969ad339dccb415afd7202e3","abstract_canon_sha256":"333690845a2f6c8e43f6ee843faf98cb1f27f5add6bc8fbcbac822be082baf08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:14.956584Z","signature_b64":"Hh1ed+JJ7HMaIX+2MT/PHYrWkxI80z1iDMRnwAZjCH3rXNxQQHHsSxEwtMlkydY2q7HWG2t+kTu+i6+zWRdRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4d6e75a4f8927eba23a7eb1dba2ff780377a0c1691aec3354ca99f5b82deabe","last_reissued_at":"2026-07-05T05:49:14.956106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:14.956106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Language Maps for Robot Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Andy Zeng, Chenguang Huang, Oier Mees, Wolfram Burgard","submitted_at":"2022-10-11T18:13:20Z","abstract_excerpt":"Grounding language to the visual observations of a navigating agent can be performed using off-the-shelf visual-language models pretrained on Internet-scale data (e.g., image captions). While this is useful for matching images to natural language descriptions of object goals, it remains disjoint from the process of mapping the environment, so that it lacks the spatial precision of classic geometric maps. To address this problem, we propose VLMaps, a spatial map representation that directly fuses pretrained visual-language features with a 3D reconstruction of the physical world. VLMaps can be a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05714","kind":"arxiv","version":4},"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/2210.05714/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":"2210.05714","created_at":"2026-07-05T05:49:14.956166+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.05714v4","created_at":"2026-07-05T05:49:14.956166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05714","created_at":"2026-07-05T05:49:14.956166+00:00"},{"alias_kind":"pith_short_12","alias_value":"UTLOOWSPRET6","created_at":"2026-07-05T05:49:14.956166+00:00"},{"alias_kind":"pith_short_16","alias_value":"UTLOOWSPRET6XIR2","created_at":"2026-07-05T05:49:14.956166+00:00"},{"alias_kind":"pith_short_8","alias_value":"UTLOOWSP","created_at":"2026-07-05T05:49:14.956166+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03374","citing_title":"eMEM: A Hybrid Spatio-Temporal Memory System For Embodied Agents","ref_index":17,"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":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26239","citing_title":"Sentinel: Embodied Cooperative Spatial Reasoning and Planning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23165","citing_title":"Autonomous Frontier-Based Exploration with VLM Guidance","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2412.06224","citing_title":"Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2307.05973","citing_title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22439","citing_title":"NRGS: Neural Regularization for Robust 3D Semantic Gaussian Splatting","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19536","citing_title":"LiveVLN: Breaking the Stop-and-Go Loop in Vision-Language Navigation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2303.03378","citing_title":"PaLM-E: An Embodied Multimodal Language Model","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UTLOOWSPRET6XIR2P2Y5XIX7PA","json":"https://pith.science/pith/UTLOOWSPRET6XIR2P2Y5XIX7PA.json","graph_json":"https://pith.science/api/pith-number/UTLOOWSPRET6XIR2P2Y5XIX7PA/graph.json","events_json":"https://pith.science/api/pith-number/UTLOOWSPRET6XIR2P2Y5XIX7PA/events.json","paper":"https://pith.science/paper/UTLOOWSP"},"agent_actions":{"view_html":"https://pith.science/pith/UTLOOWSPRET6XIR2P2Y5XIX7PA","download_json":"https://pith.science/pith/UTLOOWSPRET6XIR2P2Y5XIX7PA.json","view_paper":"https://pith.science/paper/UTLOOWSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.05714&json=true","fetch_graph":"https://pith.science/api/pith-number/UTLOOWSPRET6XIR2P2Y5XIX7PA/graph.json","fetch_events":"https://pith.science/api/pith-number/UTLOOWSPRET6XIR2P2Y5XIX7PA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UTLOOWSPRET6XIR2P2Y5XIX7PA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UTLOOWSPRET6XIR2P2Y5XIX7PA/action/storage_attestation","attest_author":"https://pith.science/pith/UTLOOWSPRET6XIR2P2Y5XIX7PA/action/author_attestation","sign_citation":"https://pith.science/pith/UTLOOWSPRET6XIR2P2Y5XIX7PA/action/citation_signature","submit_replication":"https://pith.science/pith/UTLOOWSPRET6XIR2P2Y5XIX7PA/action/replication_record"}},"created_at":"2026-07-05T05:49:14.956166+00:00","updated_at":"2026-07-05T05:49:14.956166+00:00"}