{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JGEMAPG3SJPHPZ4O2Q5SNKA3CC","short_pith_number":"pith:JGEMAPG3","schema_version":"1.0","canonical_sha256":"4988c03cdb925e77e78ed43b26a81b10a298b5a5658593ebff86a6bf60178dd5","source":{"kind":"arxiv","id":"2412.09082","version":3},"attestation_state":"computed","paper":{"title":"Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guanbin Li, Liang Lin, Weikai Chen, Weixing Chen, Xinshuai Song, Yang Liu","submitted_at":"2024-12-12T09:08:13Z","abstract_excerpt":"Existing Vision-Language Navigation (VLN) methods primarily focus on single-stage navigation, limiting their effectiveness in multi-stage and long-horizon tasks within complex and dynamic environments. To address these limitations, we propose a novel VLN task, named Long-Horizon Vision-Language Navigation (LH-VLN), which emphasizes long-term planning and decision consistency across consecutive subtasks. Furthermore, to support LH-VLN, we develop an automated data generation platform NavGen, which constructs datasets with complex task structures and improves data utility through a bidirectional"},"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":"2412.09082","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T09:08:13Z","cross_cats_sorted":[],"title_canon_sha256":"b48ebe5a454722e2023a113ee3b25f9fc286c1aaf686ebe6da85751508242289","abstract_canon_sha256":"ec7a832566ae706d12bf008aad35b608c65d37f95a00e099c34dee17cc4af0e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:41.708973Z","signature_b64":"kFL36JopSKbICcbgTPrgKvV/h0briuOs6CQFwqscbMD0QMRKsG7Ql1kP81VP+rxmkq+hcFvbmKClM32+jLlsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4988c03cdb925e77e78ed43b26a81b10a298b5a5658593ebff86a6bf60178dd5","last_reissued_at":"2026-07-05T10:34:41.708452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:41.708452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guanbin Li, Liang Lin, Weikai Chen, Weixing Chen, Xinshuai Song, Yang Liu","submitted_at":"2024-12-12T09:08:13Z","abstract_excerpt":"Existing Vision-Language Navigation (VLN) methods primarily focus on single-stage navigation, limiting their effectiveness in multi-stage and long-horizon tasks within complex and dynamic environments. To address these limitations, we propose a novel VLN task, named Long-Horizon Vision-Language Navigation (LH-VLN), which emphasizes long-term planning and decision consistency across consecutive subtasks. Furthermore, to support LH-VLN, we develop an automated data generation platform NavGen, which constructs datasets with complex task structures and improves data utility through a bidirectional"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09082","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/2412.09082/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":"2412.09082","created_at":"2026-07-05T10:34:41.708518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09082v3","created_at":"2026-07-05T10:34:41.708518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09082","created_at":"2026-07-05T10:34:41.708518+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGEMAPG3SJPH","created_at":"2026-07-05T10:34:41.708518+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGEMAPG3SJPHPZ4O","created_at":"2026-07-05T10:34:41.708518+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGEMAPG3","created_at":"2026-07-05T10:34:41.708518+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08575","citing_title":"Large Multi-modal Model Cartographic Map Comprehension for Textual Locality Georeferencing","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JGEMAPG3SJPHPZ4O2Q5SNKA3CC","json":"https://pith.science/pith/JGEMAPG3SJPHPZ4O2Q5SNKA3CC.json","graph_json":"https://pith.science/api/pith-number/JGEMAPG3SJPHPZ4O2Q5SNKA3CC/graph.json","events_json":"https://pith.science/api/pith-number/JGEMAPG3SJPHPZ4O2Q5SNKA3CC/events.json","paper":"https://pith.science/paper/JGEMAPG3"},"agent_actions":{"view_html":"https://pith.science/pith/JGEMAPG3SJPHPZ4O2Q5SNKA3CC","download_json":"https://pith.science/pith/JGEMAPG3SJPHPZ4O2Q5SNKA3CC.json","view_paper":"https://pith.science/paper/JGEMAPG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09082&json=true","fetch_graph":"https://pith.science/api/pith-number/JGEMAPG3SJPHPZ4O2Q5SNKA3CC/graph.json","fetch_events":"https://pith.science/api/pith-number/JGEMAPG3SJPHPZ4O2Q5SNKA3CC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGEMAPG3SJPHPZ4O2Q5SNKA3CC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGEMAPG3SJPHPZ4O2Q5SNKA3CC/action/storage_attestation","attest_author":"https://pith.science/pith/JGEMAPG3SJPHPZ4O2Q5SNKA3CC/action/author_attestation","sign_citation":"https://pith.science/pith/JGEMAPG3SJPHPZ4O2Q5SNKA3CC/action/citation_signature","submit_replication":"https://pith.science/pith/JGEMAPG3SJPHPZ4O2Q5SNKA3CC/action/replication_record"}},"created_at":"2026-07-05T10:34:41.708518+00:00","updated_at":"2026-07-05T10:34:41.708518+00:00"}