{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:H7G66W7PFGSHTADRD2525PMLAF","short_pith_number":"pith:H7G66W7P","schema_version":"1.0","canonical_sha256":"3fcdef5bef29a47980711ebbaebd8b0154c31e6589e75237e3c35c711abf8306","source":{"kind":"arxiv","id":"2605.17249","version":1},"attestation_state":"computed","paper":{"title":"SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hailong Huang, Haoang Li, Haoyang Yang, Jingzhi Huang, Junkai Huang, Wenxuan Song, Yi Wang","submitted_at":"2026-05-17T04:12:56Z","abstract_excerpt":"Vision-Language Navigation (VLN) approaches have currently followed two primary paradigms: the end-to-end Vision-Language Model (VLM) policy fine-tuned on navigation trajectories to directly predict actions, and the zero-shot modular pipeline integrating pre-trained Multimodal Large Language Model (MLLM) for training-free generalization to unseen environments. However, end-to-end methods struggle with long-horizon navigation and lack dynamic reasoning, whereas zero-shot methods are constrained by limited spatial grounding for reliable planning and also require substantial reasoning time. To br"},"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":"2605.17249","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-17T04:12:56Z","cross_cats_sorted":[],"title_canon_sha256":"3e13e6d3b0eb2d9eba545d990adf7f578884704f02262a7e7ef9867bb6212313","abstract_canon_sha256":"81733759ea7843a0b7f123ded4993d86639996781a5846b4f7bc937211fbed0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:47.557210Z","signature_b64":"wV5RQ7KQ7yOFPW2AF67fbyQaO9jWR4i7fMuC/5p25D822QmeT7/ze3/OwiavMBfihLvTbPfj8ziAGPp1OeQOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fcdef5bef29a47980711ebbaebd8b0154c31e6589e75237e3c35c711abf8306","last_reissued_at":"2026-05-20T00:03:47.556385Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:47.556385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hailong Huang, Haoang Li, Haoyang Yang, Jingzhi Huang, Junkai Huang, Wenxuan Song, Yi Wang","submitted_at":"2026-05-17T04:12:56Z","abstract_excerpt":"Vision-Language Navigation (VLN) approaches have currently followed two primary paradigms: the end-to-end Vision-Language Model (VLM) policy fine-tuned on navigation trajectories to directly predict actions, and the zero-shot modular pipeline integrating pre-trained Multimodal Large Language Model (MLLM) for training-free generalization to unseen environments. However, end-to-end methods struggle with long-horizon navigation and lack dynamic reasoning, whereas zero-shot methods are constrained by limited spatial grounding for reliable planning and also require substantial reasoning time. To br"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17249","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/2605.17249/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T22:01:57.867632Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.791089Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"3854aaa69490222a5bd26d2bae0d80325afb11a1e3eb5e10a00f57f269084279"},"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":"2605.17249","created_at":"2026-05-20T00:03:47.556515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17249v1","created_at":"2026-05-20T00:03:47.556515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17249","created_at":"2026-05-20T00:03:47.556515+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7G66W7PFGSH","created_at":"2026-05-20T00:03:47.556515+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7G66W7PFGSHTADR","created_at":"2026-05-20T00:03:47.556515+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7G66W7P","created_at":"2026-05-20T00:03:47.556515+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/H7G66W7PFGSHTADRD2525PMLAF","json":"https://pith.science/pith/H7G66W7PFGSHTADRD2525PMLAF.json","graph_json":"https://pith.science/api/pith-number/H7G66W7PFGSHTADRD2525PMLAF/graph.json","events_json":"https://pith.science/api/pith-number/H7G66W7PFGSHTADRD2525PMLAF/events.json","paper":"https://pith.science/paper/H7G66W7P"},"agent_actions":{"view_html":"https://pith.science/pith/H7G66W7PFGSHTADRD2525PMLAF","download_json":"https://pith.science/pith/H7G66W7PFGSHTADRD2525PMLAF.json","view_paper":"https://pith.science/paper/H7G66W7P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17249&json=true","fetch_graph":"https://pith.science/api/pith-number/H7G66W7PFGSHTADRD2525PMLAF/graph.json","fetch_events":"https://pith.science/api/pith-number/H7G66W7PFGSHTADRD2525PMLAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7G66W7PFGSHTADRD2525PMLAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7G66W7PFGSHTADRD2525PMLAF/action/storage_attestation","attest_author":"https://pith.science/pith/H7G66W7PFGSHTADRD2525PMLAF/action/author_attestation","sign_citation":"https://pith.science/pith/H7G66W7PFGSHTADRD2525PMLAF/action/citation_signature","submit_replication":"https://pith.science/pith/H7G66W7PFGSHTADRD2525PMLAF/action/replication_record"}},"created_at":"2026-05-20T00:03:47.556515+00:00","updated_at":"2026-05-20T00:03:47.556515+00:00"}