{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FPIMSWZBNVZHMRIJLGUJFAZ3D2","short_pith_number":"pith:FPIMSWZB","schema_version":"1.0","canonical_sha256":"2bd0c95b216d7276450959a892833b1eaf01931f006e4f79780ebe844a107030","source":{"kind":"arxiv","id":"2407.07035","version":2},"attestation_state":"computed","paper":{"title":"Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Jialu Li, Joyce Chai, Mohit Bansal, Parisa Kordjamshidi, Qi Wu, Yanyuan Qiao, Yue Zhang, Ziqiao Ma, Zun Wang","submitted_at":"2024-07-09T16:53:36Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) has gained increasing attention over recent years and many approaches have emerged to advance their development. The remarkable achievements of foundation models have shaped the challenges and proposed methods for VLN research. In this survey, we provide a top-down review that adopts a principled framework for embodied planning and reasoning, and emphasizes the current methods and future opportunities leveraging foundation models to address VLN challenges. We hope our in-depth discussions could provide valuable resources and insights: on one hand, to milest"},"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":"2407.07035","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-09T16:53:36Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ffbac5b0fe55fdcbacfd4a22a018b5400982264bc6c869f11115e9b688df65e4","abstract_canon_sha256":"294653b91fff3cf16cf5333c9a5f2523c22b95345565efc19f292b8e6327b478"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:10.938394Z","signature_b64":"Y694LHfioscLbmFolhV/FT2Eo+SF6hpG1q4+TQdaSEVjmmDkqSF23/KzJp69FHIF+mrTIjBmolveOnojfzvdCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bd0c95b216d7276450959a892833b1eaf01931f006e4f79780ebe844a107030","last_reissued_at":"2026-07-05T09:55:10.937941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:10.937941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Jialu Li, Joyce Chai, Mohit Bansal, Parisa Kordjamshidi, Qi Wu, Yanyuan Qiao, Yue Zhang, Ziqiao Ma, Zun Wang","submitted_at":"2024-07-09T16:53:36Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) has gained increasing attention over recent years and many approaches have emerged to advance their development. The remarkable achievements of foundation models have shaped the challenges and proposed methods for VLN research. In this survey, we provide a top-down review that adopts a principled framework for embodied planning and reasoning, and emphasizes the current methods and future opportunities leveraging foundation models to address VLN challenges. We hope our in-depth discussions could provide valuable resources and insights: on one hand, to milest"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07035","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/2407.07035/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":"2407.07035","created_at":"2026-07-05T09:55:10.937999+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07035v2","created_at":"2026-07-05T09:55:10.937999+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07035","created_at":"2026-07-05T09:55:10.937999+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPIMSWZBNVZH","created_at":"2026-07-05T09:55:10.937999+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPIMSWZBNVZHMRIJ","created_at":"2026-07-05T09:55:10.937999+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPIMSWZB","created_at":"2026-07-05T09:55:10.937999+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23565","citing_title":"HoloAgent-0: A Unified Embodied Agent Framework with 3D Spatial Memory","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22424","citing_title":"FlowDec: Temporal Conditional Flow Decorruptor for Robust Continuous Vision-Language Navigation","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02417","citing_title":"LIME: Learning Intent-aware Camera Motion from Egocentric Video","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31121","citing_title":"TARIC: Memory-Augmented Traversability-Aware Outdoor VLN under Interrupted Semantic Cues","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30557","citing_title":"Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2603.05377","citing_title":"OpenFrontier: General Navigation with Visual-Language Grounded Frontiers","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21363","citing_title":"A Deployable Embodied Vision-Language Navigation System with Hierarchical Cognition and Context-Aware Exploration","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2508.07642","citing_title":"Breaking Down and Building Up: Mixture of Skill-Based Vision-and-Language Navigation Agents","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2508.09547","citing_title":"GoViG: Goal-Conditioned Visual Navigation Instruction Generation via Multimodal Reasoning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2412.06224","citing_title":"Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13328","citing_title":"What Limits Vision-and-Language Navigation ?","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27620","citing_title":"SpaAct: Spatially-Activated Transition Learning with Curriculum Adaptation for Vision-Language Navigation","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09874","citing_title":"EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21363","citing_title":"A Deployable Embodied Vision-Language Navigation System with Hierarchical Cognition and Context-Aware Exploration","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18223","citing_title":"Instruction-as-State: Environment-Guided and State-Conditioned Semantic Understanding for Embodied Navigation","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FPIMSWZBNVZHMRIJLGUJFAZ3D2","json":"https://pith.science/pith/FPIMSWZBNVZHMRIJLGUJFAZ3D2.json","graph_json":"https://pith.science/api/pith-number/FPIMSWZBNVZHMRIJLGUJFAZ3D2/graph.json","events_json":"https://pith.science/api/pith-number/FPIMSWZBNVZHMRIJLGUJFAZ3D2/events.json","paper":"https://pith.science/paper/FPIMSWZB"},"agent_actions":{"view_html":"https://pith.science/pith/FPIMSWZBNVZHMRIJLGUJFAZ3D2","download_json":"https://pith.science/pith/FPIMSWZBNVZHMRIJLGUJFAZ3D2.json","view_paper":"https://pith.science/paper/FPIMSWZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07035&json=true","fetch_graph":"https://pith.science/api/pith-number/FPIMSWZBNVZHMRIJLGUJFAZ3D2/graph.json","fetch_events":"https://pith.science/api/pith-number/FPIMSWZBNVZHMRIJLGUJFAZ3D2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPIMSWZBNVZHMRIJLGUJFAZ3D2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPIMSWZBNVZHMRIJLGUJFAZ3D2/action/storage_attestation","attest_author":"https://pith.science/pith/FPIMSWZBNVZHMRIJLGUJFAZ3D2/action/author_attestation","sign_citation":"https://pith.science/pith/FPIMSWZBNVZHMRIJLGUJFAZ3D2/action/citation_signature","submit_replication":"https://pith.science/pith/FPIMSWZBNVZHMRIJLGUJFAZ3D2/action/replication_record"}},"created_at":"2026-07-05T09:55:10.937999+00:00","updated_at":"2026-07-05T09:55:10.937999+00:00"}