{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SUN2OKKTSQXZQGROWQWAN2XZGC","short_pith_number":"pith:SUN2OKKT","schema_version":"1.0","canonical_sha256":"951ba72953942f981a2eb42c06eaf930befadc35aee3eda03a59eb1b6c40c3d4","source":{"kind":"arxiv","id":"2508.16654","version":3},"attestation_state":"computed","paper":{"title":"MSNav: Zero-Shot Vision-and-Language Navigation with Dynamic Memory and LLM Spatial Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenghao Liu, Huiling Duan, Jiachen Zhang, Minghao Zhang, Songfang Huang, Zhimu Zhou","submitted_at":"2025-08-20T05:41:22Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) requires an agent to interpret natural language instructions and navigate complex environments. Current approaches often adopt a \"black-box\" paradigm, where a single Large Language Model (LLM) makes end-to-end decisions. However, it is plagued by critical vulnerabilities, including poor spatial reasoning, weak cross-modal grounding, and memory overload in long-horizon tasks. To systematically address these issues, we propose Memory Spatial Navigation(MSNav), a framework that fuses three modules into a synergistic architecture, which transforms fragile infer"},"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":"2508.16654","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-20T05:41:22Z","cross_cats_sorted":[],"title_canon_sha256":"a99aa882da96b2db241e1a9f33271a0387471c3bccc12d620b03c2a5c71a18df","abstract_canon_sha256":"9dc4b19dd3565ef8a5c926934a832baf25f94492d4bafa007174ba09b3cca8e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:06.923852Z","signature_b64":"UGDM4r10W2hFcy4OvyNKye9kZwAVHMpoS59C/Zv4mVPPN4HEAS+4W5PUf27ZThDnkfCLi2jMABRpeJuSUqwICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"951ba72953942f981a2eb42c06eaf930befadc35aee3eda03a59eb1b6c40c3d4","last_reissued_at":"2026-07-05T12:08:06.923339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:06.923339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MSNav: Zero-Shot Vision-and-Language Navigation with Dynamic Memory and LLM Spatial Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenghao Liu, Huiling Duan, Jiachen Zhang, Minghao Zhang, Songfang Huang, Zhimu Zhou","submitted_at":"2025-08-20T05:41:22Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) requires an agent to interpret natural language instructions and navigate complex environments. Current approaches often adopt a \"black-box\" paradigm, where a single Large Language Model (LLM) makes end-to-end decisions. However, it is plagued by critical vulnerabilities, including poor spatial reasoning, weak cross-modal grounding, and memory overload in long-horizon tasks. To systematically address these issues, we propose Memory Spatial Navigation(MSNav), a framework that fuses three modules into a synergistic architecture, which transforms fragile infer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16654","kind":"arxiv","version":3},"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/2508.16654/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":"2508.16654","created_at":"2026-07-05T12:08:06.923420+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.16654v3","created_at":"2026-07-05T12:08:06.923420+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16654","created_at":"2026-07-05T12:08:06.923420+00:00"},{"alias_kind":"pith_short_12","alias_value":"SUN2OKKTSQXZ","created_at":"2026-07-05T12:08:06.923420+00:00"},{"alias_kind":"pith_short_16","alias_value":"SUN2OKKTSQXZQGRO","created_at":"2026-07-05T12:08:06.923420+00:00"},{"alias_kind":"pith_short_8","alias_value":"SUN2OKKT","created_at":"2026-07-05T12:08:06.923420+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SUN2OKKTSQXZQGROWQWAN2XZGC","json":"https://pith.science/pith/SUN2OKKTSQXZQGROWQWAN2XZGC.json","graph_json":"https://pith.science/api/pith-number/SUN2OKKTSQXZQGROWQWAN2XZGC/graph.json","events_json":"https://pith.science/api/pith-number/SUN2OKKTSQXZQGROWQWAN2XZGC/events.json","paper":"https://pith.science/paper/SUN2OKKT"},"agent_actions":{"view_html":"https://pith.science/pith/SUN2OKKTSQXZQGROWQWAN2XZGC","download_json":"https://pith.science/pith/SUN2OKKTSQXZQGROWQWAN2XZGC.json","view_paper":"https://pith.science/paper/SUN2OKKT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.16654&json=true","fetch_graph":"https://pith.science/api/pith-number/SUN2OKKTSQXZQGROWQWAN2XZGC/graph.json","fetch_events":"https://pith.science/api/pith-number/SUN2OKKTSQXZQGROWQWAN2XZGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SUN2OKKTSQXZQGROWQWAN2XZGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SUN2OKKTSQXZQGROWQWAN2XZGC/action/storage_attestation","attest_author":"https://pith.science/pith/SUN2OKKTSQXZQGROWQWAN2XZGC/action/author_attestation","sign_citation":"https://pith.science/pith/SUN2OKKTSQXZQGROWQWAN2XZGC/action/citation_signature","submit_replication":"https://pith.science/pith/SUN2OKKTSQXZQGROWQWAN2XZGC/action/replication_record"}},"created_at":"2026-07-05T12:08:06.923420+00:00","updated_at":"2026-07-05T12:08:06.923420+00:00"}