{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MRA4A543LHD2O66M5T2ACBWKYT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"92217dcbfb7c62cb6ffc311ce492a5e1c4ab9f05d0a4d5e8304d4af8c44fbdc4","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-13T05:32:57Z","title_canon_sha256":"25ca7832ed7a40cb68973a895ce7572dab094df98585e7a7a4cceff1395b5899"},"schema_version":"1.0","source":{"id":"2503.10069","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10069","created_at":"2026-07-05T11:22:37Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10069v2","created_at":"2026-07-05T11:22:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10069","created_at":"2026-07-05T11:22:37Z"},{"alias_kind":"pith_short_12","alias_value":"MRA4A543LHD2","created_at":"2026-07-05T11:22:37Z"},{"alias_kind":"pith_short_16","alias_value":"MRA4A543LHD2O66M","created_at":"2026-07-05T11:22:37Z"},{"alias_kind":"pith_short_8","alias_value":"MRA4A543","created_at":"2026-07-05T11:22:37Z"}],"graph_snapshots":[{"event_id":"sha256:891fc3a9084a95b4db532ac39c7d8669e28fcf6220a03ac9b743d0be6f0314c8","target":"graph","created_at":"2026-07-05T11:22:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.10069/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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)-","authors_text":"Feras Dayoub, Jiatong Xia, Qi Wu, Wenqi Lyu, Xiangyu Shi, Yanyuan Qiao, Zerui Li","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-13T05:32:57Z","title":"SmartWay: Enhanced Waypoint Prediction and Backtracking for Zero-Shot Vision-and-Language Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10069","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:949435be90cc852cbdbbb4550fa422ea9c3aabe12aae43bff0e93cd8c2a653e6","target":"record","created_at":"2026-07-05T11:22:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"92217dcbfb7c62cb6ffc311ce492a5e1c4ab9f05d0a4d5e8304d4af8c44fbdc4","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-13T05:32:57Z","title_canon_sha256":"25ca7832ed7a40cb68973a895ce7572dab094df98585e7a7a4cceff1395b5899"},"schema_version":"1.0","source":{"id":"2503.10069","kind":"arxiv","version":2}},"canonical_sha256":"6441c0779b59c7a77bccecf40106cac4db7c2f3f4135f702357a7c737fa39093","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6441c0779b59c7a77bccecf40106cac4db7c2f3f4135f702357a7c737fa39093","first_computed_at":"2026-07-05T11:22:37.680784Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:37.680784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k27k2BKH1kk1SCrDGo812/T/4rzbETwa6K5DrSA7ZpxdNcx/kxrimhHDXPO1Uz2jZ143uD8jNgMQwlFOJ7PhAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:37.681457Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.10069","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:949435be90cc852cbdbbb4550fa422ea9c3aabe12aae43bff0e93cd8c2a653e6","sha256:891fc3a9084a95b4db532ac39c7d8669e28fcf6220a03ac9b743d0be6f0314c8"],"state_sha256":"f43bfc6b6aab72ce4d5f047b441234316c0914b2a9e67dcc6c902147d3872457"}