{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OJQDLP7H5CB3MOMJ26RNU7E552","short_pith_number":"pith:OJQDLP7H","schema_version":"1.0","canonical_sha256":"726035bfe7e883b63989d7a2da7c9deeb59b30f4c99224a3a4688c7e73be3d88","source":{"kind":"arxiv","id":"2403.07376","version":2},"attestation_state":"computed","paper":{"title":"NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bingqian Lin, Hang Xu, Jianhua Han, Jiaqi Chen, Shikui Ma, Xiaodan Liang, Xiaojun Chang, Yunshuang Nie, Ziming Wei","submitted_at":"2024-03-12T07:27:02Z","abstract_excerpt":"Vision-and-Language Navigation (VLN), as a crucial research problem of Embodied AI, requires an embodied agent to navigate through complex 3D environments following natural language instructions. Recent research has highlighted the promising capacity of large language models (LLMs) in VLN by improving navigational reasoning accuracy and interpretability. However, their predominant use in an offline manner usually suffers from substantial domain gap between the VLN task and the LLM training corpus. This paper introduces a novel strategy called Navigational Chain-of-Thought (NavCoT), where we fu"},"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":"2403.07376","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T07:27:02Z","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"title_canon_sha256":"9071f699cac00d9d8491dcb9d7ab844de295ee572f2e27a94312fb2eb148a1c8","abstract_canon_sha256":"0f81e4baf56617bfc8f7834ef7893c58116ca6eb42108357b304958bc3eda458"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:24.810665Z","signature_b64":"kkrNsDoh/zFyYlMDng916GkYY6nrpd7Bpwr9izqnbOdgoLTLZlXlD/lIR81CFvtOY0LYmpJ7ksc/khxVvCs4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"726035bfe7e883b63989d7a2da7c9deeb59b30f4c99224a3a4688c7e73be3d88","last_reissued_at":"2026-07-05T10:37:24.810026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:24.810026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bingqian Lin, Hang Xu, Jianhua Han, Jiaqi Chen, Shikui Ma, Xiaodan Liang, Xiaojun Chang, Yunshuang Nie, Ziming Wei","submitted_at":"2024-03-12T07:27:02Z","abstract_excerpt":"Vision-and-Language Navigation (VLN), as a crucial research problem of Embodied AI, requires an embodied agent to navigate through complex 3D environments following natural language instructions. Recent research has highlighted the promising capacity of large language models (LLMs) in VLN by improving navigational reasoning accuracy and interpretability. However, their predominant use in an offline manner usually suffers from substantial domain gap between the VLN task and the LLM training corpus. This paper introduces a novel strategy called Navigational Chain-of-Thought (NavCoT), where we fu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07376","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/2403.07376/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":"2403.07376","created_at":"2026-07-05T10:37:24.810119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.07376v2","created_at":"2026-07-05T10:37:24.810119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07376","created_at":"2026-07-05T10:37:24.810119+00:00"},{"alias_kind":"pith_short_12","alias_value":"OJQDLP7H5CB3","created_at":"2026-07-05T10:37:24.810119+00:00"},{"alias_kind":"pith_short_16","alias_value":"OJQDLP7H5CB3MOMJ","created_at":"2026-07-05T10:37:24.810119+00:00"},{"alias_kind":"pith_short_8","alias_value":"OJQDLP7H","created_at":"2026-07-05T10:37:24.810119+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08992","citing_title":"SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30367","citing_title":"FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2502.13451","citing_title":"MapNav: A Novel Memory Representation via Annotated Semantic Maps for Vision-and-Language Navigation","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OJQDLP7H5CB3MOMJ26RNU7E552","json":"https://pith.science/pith/OJQDLP7H5CB3MOMJ26RNU7E552.json","graph_json":"https://pith.science/api/pith-number/OJQDLP7H5CB3MOMJ26RNU7E552/graph.json","events_json":"https://pith.science/api/pith-number/OJQDLP7H5CB3MOMJ26RNU7E552/events.json","paper":"https://pith.science/paper/OJQDLP7H"},"agent_actions":{"view_html":"https://pith.science/pith/OJQDLP7H5CB3MOMJ26RNU7E552","download_json":"https://pith.science/pith/OJQDLP7H5CB3MOMJ26RNU7E552.json","view_paper":"https://pith.science/paper/OJQDLP7H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.07376&json=true","fetch_graph":"https://pith.science/api/pith-number/OJQDLP7H5CB3MOMJ26RNU7E552/graph.json","fetch_events":"https://pith.science/api/pith-number/OJQDLP7H5CB3MOMJ26RNU7E552/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OJQDLP7H5CB3MOMJ26RNU7E552/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OJQDLP7H5CB3MOMJ26RNU7E552/action/storage_attestation","attest_author":"https://pith.science/pith/OJQDLP7H5CB3MOMJ26RNU7E552/action/author_attestation","sign_citation":"https://pith.science/pith/OJQDLP7H5CB3MOMJ26RNU7E552/action/citation_signature","submit_replication":"https://pith.science/pith/OJQDLP7H5CB3MOMJ26RNU7E552/action/replication_record"}},"created_at":"2026-07-05T10:37:24.810119+00:00","updated_at":"2026-07-05T10:37:24.810119+00:00"}