{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TR74Z6DCPU6U6DIQJOVV34ODKB","short_pith_number":"pith:TR74Z6DC","schema_version":"1.0","canonical_sha256":"9c7fccf8627d3d4f0d104bab5df1c35073cc9c616c1a3ac8fae906fa9d10da53","source":{"kind":"arxiv","id":"2603.14807","version":2},"attestation_state":"computed","paper":{"title":"HiMemVLN: Enhancing Reliability of Open-Source Zero-Shot Vision-and-Language Navigation with Hierarchical Memory System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Ce Hao, Cui Miao, Jingyuan Sun, Kailin Lyu, Kangyi Wu, Lianyu Hu, Long Xiao, Ning Yang, Pengna Li, Qingyi Si, Xiuyu Hu, Zihang Wang","submitted_at":"2026-03-16T04:23:29Z","abstract_excerpt":"LLM-based agents have demonstrated impressive zero-shot performance in vision-language navigation (VLN) tasks. However, most zero-shot methods primarily rely on closed-source LLMs as navigators, which face challenges related to high token costs and potential data leakage risks. Recent efforts have attempted to address this by using open-source LLMs combined with a spatiotemporal CoT framework, but they still fall far short compared to closed-source models. In this work, we identify a critical issue, Navigation Amnesia, through a detailed analysis of the navigation process. This issue leads to "},"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":"2603.14807","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-16T04:23:29Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"8610b2ea63092cbbc3b123470ed085f63199d833ee10328922ec6b454a8eb9b0","abstract_canon_sha256":"a34b9b8f94bc1f9625bb1ab7706f0f8e1af8f1ee85e15d97ab0452fdda7a8adc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:20:45.788272Z","signature_b64":"vkljDOKNt0FcKvNY8vOt0c4u1xSnrSgwlBersIVd438pTLTZmG0ocUMd0AvoxfPFjqUMfR+nb/3hzIqB8WRdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c7fccf8627d3d4f0d104bab5df1c35073cc9c616c1a3ac8fae906fa9d10da53","last_reissued_at":"2026-07-21T01:20:45.787222Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:20:45.787222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiMemVLN: Enhancing Reliability of Open-Source Zero-Shot Vision-and-Language Navigation with Hierarchical Memory System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Ce Hao, Cui Miao, Jingyuan Sun, Kailin Lyu, Kangyi Wu, Lianyu Hu, Long Xiao, Ning Yang, Pengna Li, Qingyi Si, Xiuyu Hu, Zihang Wang","submitted_at":"2026-03-16T04:23:29Z","abstract_excerpt":"LLM-based agents have demonstrated impressive zero-shot performance in vision-language navigation (VLN) tasks. However, most zero-shot methods primarily rely on closed-source LLMs as navigators, which face challenges related to high token costs and potential data leakage risks. Recent efforts have attempted to address this by using open-source LLMs combined with a spatiotemporal CoT framework, but they still fall far short compared to closed-source models. In this work, we identify a critical issue, Navigation Amnesia, through a detailed analysis of the navigation process. This issue leads to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.14807","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/2603.14807/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":"2603.14807","created_at":"2026-07-21T01:20:45.787698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.14807v2","created_at":"2026-07-21T01:20:45.787698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.14807","created_at":"2026-07-21T01:20:45.787698+00:00"},{"alias_kind":"pith_short_12","alias_value":"TR74Z6DCPU6U","created_at":"2026-07-21T01:20:45.787698+00:00"},{"alias_kind":"pith_short_16","alias_value":"TR74Z6DCPU6U6DIQ","created_at":"2026-07-21T01:20:45.787698+00:00"},{"alias_kind":"pith_short_8","alias_value":"TR74Z6DC","created_at":"2026-07-21T01:20:45.787698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2605.17249","citing_title":"SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.27582","citing_title":"Uni-LaViRA: Language-Vision-Robot Actions Translation for Unified Embodied Navigation","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17249","citing_title":"SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27620","citing_title":"SpaAct: Spatially-Activated Transition Learning with Curriculum Adaptation for Vision-Language Navigation","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17473","citing_title":"Dual-Anchoring: Addressing State Drift in Vision-Language Navigation","ref_index":151,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17407","citing_title":"Think before Go: Hierarchical Reasoning for Image-goal Navigation","ref_index":133,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TR74Z6DCPU6U6DIQJOVV34ODKB","json":"https://pith.science/pith/TR74Z6DCPU6U6DIQJOVV34ODKB.json","graph_json":"https://pith.science/api/pith-number/TR74Z6DCPU6U6DIQJOVV34ODKB/graph.json","events_json":"https://pith.science/api/pith-number/TR74Z6DCPU6U6DIQJOVV34ODKB/events.json","paper":"https://pith.science/paper/TR74Z6DC"},"agent_actions":{"view_html":"https://pith.science/pith/TR74Z6DCPU6U6DIQJOVV34ODKB","download_json":"https://pith.science/pith/TR74Z6DCPU6U6DIQJOVV34ODKB.json","view_paper":"https://pith.science/paper/TR74Z6DC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.14807&json=true","fetch_graph":"https://pith.science/api/pith-number/TR74Z6DCPU6U6DIQJOVV34ODKB/graph.json","fetch_events":"https://pith.science/api/pith-number/TR74Z6DCPU6U6DIQJOVV34ODKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TR74Z6DCPU6U6DIQJOVV34ODKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TR74Z6DCPU6U6DIQJOVV34ODKB/action/storage_attestation","attest_author":"https://pith.science/pith/TR74Z6DCPU6U6DIQJOVV34ODKB/action/author_attestation","sign_citation":"https://pith.science/pith/TR74Z6DCPU6U6DIQJOVV34ODKB/action/citation_signature","submit_replication":"https://pith.science/pith/TR74Z6DCPU6U6DIQJOVV34ODKB/action/replication_record"}},"created_at":"2026-07-21T01:20:45.787698+00:00","updated_at":"2026-07-21T01:20:45.787698+00:00"}