{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GHNNX26G57WDDK2OZPGWAPEOF7","short_pith_number":"pith:GHNNX26G","schema_version":"1.0","canonical_sha256":"31dadbebc6efec31ab4ecbcd603c8e2fc82c2523cbabf1801a47de292cccc990","source":{"kind":"arxiv","id":"2605.06317","version":3},"attestation_state":"computed","paper":{"title":"NavOne: One-Step Global Planning for Vision-Language Navigation on Top-Down Maps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"NavOne reformulates vision-language navigation as one-step global path planning via direct dense path probability prediction on pre-built top-down maps.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenxi Zheng, Dijia Zhan, Jie Tang, Jinyi Li, Shaoyu Huang, Xuemiao Xu, Yong Li","submitted_at":"2026-05-07T14:16:58Z","abstract_excerpt":"Existing Vision-Language Navigation (VLN) methods typically adopt an egocentric, step-by-step paradigm, which struggles with error accumulation and limits efficiency. While recent approaches attempt to leverage pre-built environment maps, they often rely on incrementally updating memory graphs or scoring discrete path proposals, which restricts continuous spatial reasoning and creates discrete bottlenecks. We propose Top-Down VLN (TD-VLN), reformulating navigation as a one-step global path planning problem on pre-built top-down maps, supported by our newly constructed R2R-TopDown dataset. To s"},"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":"2605.06317","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-07T14:16:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a6a71c01e96c5dc4c7f7688e226327084abe646621eace79b75b911496d7eb11","abstract_canon_sha256":"e4a237b2c71b9f66e9cf3d2f6e24c74288d2b7af3f693af7414ff5c7878478f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:46.230369Z","signature_b64":"gK6wwDsukit7ZT5RXckOqb9JiJSLlZrdwah7jUsmFEiio7mPC43P4ygScSRJyWmDK6Zd20rpXDN2HYcGMeu6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31dadbebc6efec31ab4ecbcd603c8e2fc82c2523cbabf1801a47de292cccc990","last_reissued_at":"2026-05-20T00:05:46.229750Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:46.229750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NavOne: One-Step Global Planning for Vision-Language Navigation on Top-Down Maps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"NavOne reformulates vision-language navigation as one-step global path planning via direct dense path probability prediction on pre-built top-down maps.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenxi Zheng, Dijia Zhan, Jie Tang, Jinyi Li, Shaoyu Huang, Xuemiao Xu, Yong Li","submitted_at":"2026-05-07T14:16:58Z","abstract_excerpt":"Existing Vision-Language Navigation (VLN) methods typically adopt an egocentric, step-by-step paradigm, which struggles with error accumulation and limits efficiency. While recent approaches attempt to leverage pre-built environment maps, they often rely on incrementally updating memory graphs or scoring discrete path proposals, which restricts continuous spatial reasoning and creates discrete bottlenecks. We propose Top-Down VLN (TD-VLN), reformulating navigation as a one-step global path planning problem on pre-built top-down maps, supported by our newly constructed R2R-TopDown dataset. To s"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"NavOne achieves state-of-the-art performance among map-based VLN methods, with a planning-stage speedup of 8x over existing map-based baselines and 80x over egocentric methods, enabling highly efficient global navigation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The approach assumes the availability of pre-built top-down maps and that direct prediction of dense path probabilities on these maps can effectively solve the navigation task without the error accumulation issues of step-by-step methods.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"NavOne enables one-step global navigation planning on top-down maps using a unified multi-modal framework, achieving state-of-the-art results and up to 80x speedup on the new R2R-TopDown dataset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"NavOne reformulates vision-language navigation as one-step global path planning via direct dense path probability prediction on pre-built top-down maps.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5c86ceeacc539a6a65e9c8933b3d15f0ec77576f2e3ee8d0baf20845aae204b8"},"source":{"id":"2605.06317","kind":"arxiv","version":3},"verdict":{"id":"0be83d16-86ba-499c-aa7f-36a4049af79e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T00:44:32.395108Z","strongest_claim":"NavOne achieves state-of-the-art performance among map-based VLN methods, with a planning-stage speedup of 8x over existing map-based baselines and 80x over egocentric methods, enabling highly efficient global navigation.","one_line_summary":"NavOne enables one-step global navigation planning on top-down maps using a unified multi-modal framework, achieving state-of-the-art results and up to 80x speedup on the new R2R-TopDown dataset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The approach assumes the availability of pre-built top-down maps and that direct prediction of dense path probabilities on these maps can effectively solve the navigation task without the error accumulation issues of step-by-step methods.","pith_extraction_headline":"NavOne reformulates vision-language navigation as one-step global path planning via direct dense path probability prediction on pre-built top-down maps."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.06317/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T18:31:19.465290Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T12:48:58.703983Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d53de2d18b7638cf92a753f05c131a011f7616d8fe72529ea4a2d3d8b609cd82"},"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":"2605.06317","created_at":"2026-05-20T00:05:46.229828+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.06317v3","created_at":"2026-05-20T00:05:46.229828+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.06317","created_at":"2026-05-20T00:05:46.229828+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHNNX26G57WD","created_at":"2026-05-20T00:05:46.229828+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHNNX26G57WDDK2O","created_at":"2026-05-20T00:05:46.229828+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHNNX26G","created_at":"2026-05-20T00:05:46.229828+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/GHNNX26G57WDDK2OZPGWAPEOF7","json":"https://pith.science/pith/GHNNX26G57WDDK2OZPGWAPEOF7.json","graph_json":"https://pith.science/api/pith-number/GHNNX26G57WDDK2OZPGWAPEOF7/graph.json","events_json":"https://pith.science/api/pith-number/GHNNX26G57WDDK2OZPGWAPEOF7/events.json","paper":"https://pith.science/paper/GHNNX26G"},"agent_actions":{"view_html":"https://pith.science/pith/GHNNX26G57WDDK2OZPGWAPEOF7","download_json":"https://pith.science/pith/GHNNX26G57WDDK2OZPGWAPEOF7.json","view_paper":"https://pith.science/paper/GHNNX26G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.06317&json=true","fetch_graph":"https://pith.science/api/pith-number/GHNNX26G57WDDK2OZPGWAPEOF7/graph.json","fetch_events":"https://pith.science/api/pith-number/GHNNX26G57WDDK2OZPGWAPEOF7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHNNX26G57WDDK2OZPGWAPEOF7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHNNX26G57WDDK2OZPGWAPEOF7/action/storage_attestation","attest_author":"https://pith.science/pith/GHNNX26G57WDDK2OZPGWAPEOF7/action/author_attestation","sign_citation":"https://pith.science/pith/GHNNX26G57WDDK2OZPGWAPEOF7/action/citation_signature","submit_replication":"https://pith.science/pith/GHNNX26G57WDDK2OZPGWAPEOF7/action/replication_record"}},"created_at":"2026-05-20T00:05:46.229828+00:00","updated_at":"2026-05-20T00:05:46.229828+00:00"}