{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MRA4A543LHD2O66M5T2ACBWKYT","short_pith_number":"pith:MRA4A543","schema_version":"1.0","canonical_sha256":"6441c0779b59c7a77bccecf40106cac4db7c2f3f4135f702357a7c737fa39093","source":{"kind":"arxiv","id":"2503.10069","version":2},"attestation_state":"computed","paper":{"title":"SmartWay: Enhanced Waypoint Prediction and Backtracking for Zero-Shot Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Feras Dayoub, Jiatong Xia, Qi Wu, Wenqi Lyu, Xiangyu Shi, Yanyuan Qiao, Zerui Li","submitted_at":"2025-03-13T05:32:57Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) in continuous environments requires agents to interpret natural language instructions while navigating unconstrained 3D spaces. Existing VLN-CE frameworks rely on a two-stage approach: a waypoint predictor to generate waypoints and a navigator to execute movements. However, current waypoint predictors struggle with spatial awareness, while navigators lack historical reasoning and backtracking capabilities, limiting adaptability. We propose a zero-shot VLN-CE framework integrating an enhanced waypoint predictor with a Multi-modal Large Language Model (MLLM)-"},"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":"2503.10069","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-13T05:32:57Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"25ca7832ed7a40cb68973a895ce7572dab094df98585e7a7a4cceff1395b5899","abstract_canon_sha256":"92217dcbfb7c62cb6ffc311ce492a5e1c4ab9f05d0a4d5e8304d4af8c44fbdc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:37.681457Z","signature_b64":"k27k2BKH1kk1SCrDGo812/T/4rzbETwa6K5DrSA7ZpxdNcx/kxrimhHDXPO1Uz2jZ143uD8jNgMQwlFOJ7PhAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6441c0779b59c7a77bccecf40106cac4db7c2f3f4135f702357a7c737fa39093","last_reissued_at":"2026-07-05T11:22:37.680784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:37.680784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SmartWay: Enhanced Waypoint Prediction and Backtracking for Zero-Shot Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Feras Dayoub, Jiatong Xia, Qi Wu, Wenqi Lyu, Xiangyu Shi, Yanyuan Qiao, Zerui Li","submitted_at":"2025-03-13T05:32:57Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) in continuous environments requires agents to interpret natural language instructions while navigating unconstrained 3D spaces. Existing VLN-CE frameworks rely on a two-stage approach: a waypoint predictor to generate waypoints and a navigator to execute movements. However, current waypoint predictors struggle with spatial awareness, while navigators lack historical reasoning and backtracking capabilities, limiting adaptability. We propose a zero-shot VLN-CE framework integrating an enhanced waypoint predictor with a Multi-modal Large Language Model (MLLM)-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10069","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/2503.10069/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":"2503.10069","created_at":"2026-07-05T11:22:37.680861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10069v2","created_at":"2026-07-05T11:22:37.680861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10069","created_at":"2026-07-05T11:22:37.680861+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRA4A543LHD2","created_at":"2026-07-05T11:22:37.680861+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRA4A543LHD2O66M","created_at":"2026-07-05T11:22:37.680861+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRA4A543","created_at":"2026-07-05T11:22:37.680861+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07244","citing_title":"Beyond Waypoints: A Trajectory-Centric Waypointing Paradigm for Vision-Language Navigation","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MRA4A543LHD2O66M5T2ACBWKYT","json":"https://pith.science/pith/MRA4A543LHD2O66M5T2ACBWKYT.json","graph_json":"https://pith.science/api/pith-number/MRA4A543LHD2O66M5T2ACBWKYT/graph.json","events_json":"https://pith.science/api/pith-number/MRA4A543LHD2O66M5T2ACBWKYT/events.json","paper":"https://pith.science/paper/MRA4A543"},"agent_actions":{"view_html":"https://pith.science/pith/MRA4A543LHD2O66M5T2ACBWKYT","download_json":"https://pith.science/pith/MRA4A543LHD2O66M5T2ACBWKYT.json","view_paper":"https://pith.science/paper/MRA4A543","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10069&json=true","fetch_graph":"https://pith.science/api/pith-number/MRA4A543LHD2O66M5T2ACBWKYT/graph.json","fetch_events":"https://pith.science/api/pith-number/MRA4A543LHD2O66M5T2ACBWKYT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRA4A543LHD2O66M5T2ACBWKYT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRA4A543LHD2O66M5T2ACBWKYT/action/storage_attestation","attest_author":"https://pith.science/pith/MRA4A543LHD2O66M5T2ACBWKYT/action/author_attestation","sign_citation":"https://pith.science/pith/MRA4A543LHD2O66M5T2ACBWKYT/action/citation_signature","submit_replication":"https://pith.science/pith/MRA4A543LHD2O66M5T2ACBWKYT/action/replication_record"}},"created_at":"2026-07-05T11:22:37.680861+00:00","updated_at":"2026-07-05T11:22:37.680861+00:00"}