{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7XQOHKZRP3PBJGTIX7KD5XNJO2","short_pith_number":"pith:7XQOHKZR","schema_version":"1.0","canonical_sha256":"fde0e3ab317ede149a68bfd43edda976a794d8fa7186b589dba7d36478e1c7c9","source":{"kind":"arxiv","id":"2410.03603","version":1},"attestation_state":"computed","paper":{"title":"LeLaN: Learning A Language-Conditioned Navigation Policy from In-the-Wild Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ajay Sridhar, Catherine Glossop, Dhruv Shah, Noriaki Hirose, Oier Mees, Sergey Levine","submitted_at":"2024-10-04T17:03:14Z","abstract_excerpt":"The world is filled with a wide variety of objects. For robots to be useful, they need the ability to find arbitrary objects described by people. In this paper, we present LeLaN(Learning Language-conditioned Navigation policy), a novel approach that consumes unlabeled, action-free egocentric data to learn scalable, language-conditioned object navigation. Our framework, LeLaN leverages the semantic knowledge of large vision-language models, as well as robotic foundation models, to label in-the-wild data from a variety of indoor and outdoor environments. We label over 130 hours of data collected"},"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":"2410.03603","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-04T17:03:14Z","cross_cats_sorted":[],"title_canon_sha256":"05419cb357435f991781ba8a07d8103d860e8aeb1870f08ae388a9d18acabdb0","abstract_canon_sha256":"70892e8c0ef65e64d24068afcaea771986569dc17ce4456f76975055039d5fd3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:03.569460Z","signature_b64":"1mBRVmrbqI6RND0PzwqqRqvNTJ+DfrhrOblqZlK89U9wysJyyXPTosLoiNy8y6Y5TIEX47kgIqwPooaA4OrSDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fde0e3ab317ede149a68bfd43edda976a794d8fa7186b589dba7d36478e1c7c9","last_reissued_at":"2026-07-05T09:16:03.568776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:03.568776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LeLaN: Learning A Language-Conditioned Navigation Policy from In-the-Wild Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ajay Sridhar, Catherine Glossop, Dhruv Shah, Noriaki Hirose, Oier Mees, Sergey Levine","submitted_at":"2024-10-04T17:03:14Z","abstract_excerpt":"The world is filled with a wide variety of objects. For robots to be useful, they need the ability to find arbitrary objects described by people. In this paper, we present LeLaN(Learning Language-conditioned Navigation policy), a novel approach that consumes unlabeled, action-free egocentric data to learn scalable, language-conditioned object navigation. Our framework, LeLaN leverages the semantic knowledge of large vision-language models, as well as robotic foundation models, to label in-the-wild data from a variety of indoor and outdoor environments. We label over 130 hours of data collected"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03603","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/2410.03603/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":"2410.03603","created_at":"2026-07-05T09:16:03.568870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03603v1","created_at":"2026-07-05T09:16:03.568870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03603","created_at":"2026-07-05T09:16:03.568870+00:00"},{"alias_kind":"pith_short_12","alias_value":"7XQOHKZRP3PB","created_at":"2026-07-05T09:16:03.568870+00:00"},{"alias_kind":"pith_short_16","alias_value":"7XQOHKZRP3PBJGTI","created_at":"2026-07-05T09:16:03.568870+00:00"},{"alias_kind":"pith_short_8","alias_value":"7XQOHKZR","created_at":"2026-07-05T09:16:03.568870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18426","citing_title":"VEGA: Learning Navigation VLAs from In-the-Wild Egocentric Video with Geometric Trajectory Supervision","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28760","citing_title":"Vision-Language Models for Deployable Social Robot Navigation: Bridging Semantic Reasoning and Low-Level Control","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16979","citing_title":"NORM-Nav: Zero-Shot Mobile Robot Navigation with Natural Language Behavioral Constraints","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07592","citing_title":"Spatio-Temporal Grounding of Large Language Models from Perception Streams","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7XQOHKZRP3PBJGTIX7KD5XNJO2","json":"https://pith.science/pith/7XQOHKZRP3PBJGTIX7KD5XNJO2.json","graph_json":"https://pith.science/api/pith-number/7XQOHKZRP3PBJGTIX7KD5XNJO2/graph.json","events_json":"https://pith.science/api/pith-number/7XQOHKZRP3PBJGTIX7KD5XNJO2/events.json","paper":"https://pith.science/paper/7XQOHKZR"},"agent_actions":{"view_html":"https://pith.science/pith/7XQOHKZRP3PBJGTIX7KD5XNJO2","download_json":"https://pith.science/pith/7XQOHKZRP3PBJGTIX7KD5XNJO2.json","view_paper":"https://pith.science/paper/7XQOHKZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03603&json=true","fetch_graph":"https://pith.science/api/pith-number/7XQOHKZRP3PBJGTIX7KD5XNJO2/graph.json","fetch_events":"https://pith.science/api/pith-number/7XQOHKZRP3PBJGTIX7KD5XNJO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7XQOHKZRP3PBJGTIX7KD5XNJO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7XQOHKZRP3PBJGTIX7KD5XNJO2/action/storage_attestation","attest_author":"https://pith.science/pith/7XQOHKZRP3PBJGTIX7KD5XNJO2/action/author_attestation","sign_citation":"https://pith.science/pith/7XQOHKZRP3PBJGTIX7KD5XNJO2/action/citation_signature","submit_replication":"https://pith.science/pith/7XQOHKZRP3PBJGTIX7KD5XNJO2/action/replication_record"}},"created_at":"2026-07-05T09:16:03.568870+00:00","updated_at":"2026-07-05T09:16:03.568870+00:00"}