{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:332H6RY7ORZMVPMRKE6XINZ32P","short_pith_number":"pith:332H6RY7","schema_version":"1.0","canonical_sha256":"def47f471f7472cabd91513d74373bd3c8cf4cf53f2e4afcdf89071ae0dd9c53","source":{"kind":"arxiv","id":"2605.14801","version":1},"attestation_state":"computed","paper":{"title":"Exploring Bottlenecks in VLM-LLM Navigation: How 3D Scene Understanding Capability Impacts Zero-Shot VLN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chaoran Xiong, Ling Pei, Litao Wei, Xinhao Hu, Ziyi Xia","submitted_at":"2026-05-14T13:12:05Z","abstract_excerpt":"Zero-shot vision-and-language navigation (VLN) has gained significant attention due to its minimal data collection costs and inherent generalization. This paradigm is typically driven by the integration of pre-trained Vision-Language Models (VLMs) and Large Language Models (LLMs), where VLMs construct 3D scene graphs while LLMs handle high-level reasoning and decision-making. However, a critical bottleneck exists in this system: current 3D perception models prioritize pixel-level accuracy, directly conflicting with the strict computational limits and real-time efficiency demanded by embodied n"},"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":"2605.14801","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-14T13:12:05Z","cross_cats_sorted":[],"title_canon_sha256":"54a7c26b27d63df8e3f96ad961c7f4932470c8fcd357569583e5a84fdc05a1cb","abstract_canon_sha256":"12a0b1c8bbc1cd518a2765ecc164a40b09aed2f3c1dcd7fb0c0c3892d9a85f1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:58.356453Z","signature_b64":"nYjIpeWJ79aEhtsIRDnu+KQqOiZvn38DTU/YVrD2RHOcRG3xS7COwg9/E6U56hIVH9DZ7ro1IbFSKsajndg/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"def47f471f7472cabd91513d74373bd3c8cf4cf53f2e4afcdf89071ae0dd9c53","last_reissued_at":"2026-05-17T23:38:58.355714Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:58.355714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Bottlenecks in VLM-LLM Navigation: How 3D Scene Understanding Capability Impacts Zero-Shot VLN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chaoran Xiong, Ling Pei, Litao Wei, Xinhao Hu, Ziyi Xia","submitted_at":"2026-05-14T13:12:05Z","abstract_excerpt":"Zero-shot vision-and-language navigation (VLN) has gained significant attention due to its minimal data collection costs and inherent generalization. This paradigm is typically driven by the integration of pre-trained Vision-Language Models (VLMs) and Large Language Models (LLMs), where VLMs construct 3D scene graphs while LLMs handle high-level reasoning and decision-making. However, a critical bottleneck exists in this system: current 3D perception models prioritize pixel-level accuracy, directly conflicting with the strict computational limits and real-time efficiency demanded by embodied n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14801","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":""},"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":"2605.14801","created_at":"2026-05-17T23:38:58.355849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14801v1","created_at":"2026-05-17T23:38:58.355849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14801","created_at":"2026-05-17T23:38:58.355849+00:00"},{"alias_kind":"pith_short_12","alias_value":"332H6RY7ORZM","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"332H6RY7ORZMVPMR","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"332H6RY7","created_at":"2026-05-18T12:33:37.589309+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/332H6RY7ORZMVPMRKE6XINZ32P","json":"https://pith.science/pith/332H6RY7ORZMVPMRKE6XINZ32P.json","graph_json":"https://pith.science/api/pith-number/332H6RY7ORZMVPMRKE6XINZ32P/graph.json","events_json":"https://pith.science/api/pith-number/332H6RY7ORZMVPMRKE6XINZ32P/events.json","paper":"https://pith.science/paper/332H6RY7"},"agent_actions":{"view_html":"https://pith.science/pith/332H6RY7ORZMVPMRKE6XINZ32P","download_json":"https://pith.science/pith/332H6RY7ORZMVPMRKE6XINZ32P.json","view_paper":"https://pith.science/paper/332H6RY7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14801&json=true","fetch_graph":"https://pith.science/api/pith-number/332H6RY7ORZMVPMRKE6XINZ32P/graph.json","fetch_events":"https://pith.science/api/pith-number/332H6RY7ORZMVPMRKE6XINZ32P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/332H6RY7ORZMVPMRKE6XINZ32P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/332H6RY7ORZMVPMRKE6XINZ32P/action/storage_attestation","attest_author":"https://pith.science/pith/332H6RY7ORZMVPMRKE6XINZ32P/action/author_attestation","sign_citation":"https://pith.science/pith/332H6RY7ORZMVPMRKE6XINZ32P/action/citation_signature","submit_replication":"https://pith.science/pith/332H6RY7ORZMVPMRKE6XINZ32P/action/replication_record"}},"created_at":"2026-05-17T23:38:58.355849+00:00","updated_at":"2026-05-17T23:38:58.355849+00:00"}