{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:U56BILAPY22OBSPGM3GDH2WMC3","short_pith_number":"pith:U56BILAP","schema_version":"1.0","canonical_sha256":"a77c142c0fc6b4e0c9e666cc33eacc16c1340714905de4cb5eb9f614de1d62b2","source":{"kind":"arxiv","id":"2110.05728","version":1},"attestation_state":"computed","paper":{"title":"Rethinking the Spatial Route Prior in Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Wei Liu, Xinzhe Zhou, Yadong Mu","submitted_at":"2021-10-12T03:55:43Z","abstract_excerpt":"Vision-and-language navigation (VLN) is a trending topic which aims to navigate an intelligent agent to an expected position through natural language instructions. This work addresses the task of VLN from a previously-ignored aspect, namely the spatial route prior of the navigation scenes. A critically enabling innovation of this work is explicitly considering the spatial route prior under several different VLN settings. In a most information-rich case of knowing environment maps and admitting shortest-path prior, we observe that given an origin-destination node pair, the internal route can be"},"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":"2110.05728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-12T03:55:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"817f0e04f94763bcfd9d127b9816257cb24f023fdde21bc7a6d507135574e082","abstract_canon_sha256":"a5051d98643ce389e865b978f7c0a774fd2a3bc57020a0dc7c7fb2b49f00c15a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:05.795659Z","signature_b64":"5GRoGc8MqjQd0BzYo5ZLpJ7RQPYL1h2X5yQKO7wYnTU0llh0sTkCm6eXoc4seqHgTjyjaByIqyR0J/PP3/uCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a77c142c0fc6b4e0c9e666cc33eacc16c1340714905de4cb5eb9f614de1d62b2","last_reissued_at":"2026-07-05T03:22:05.795105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:05.795105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking the Spatial Route Prior in Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Wei Liu, Xinzhe Zhou, Yadong Mu","submitted_at":"2021-10-12T03:55:43Z","abstract_excerpt":"Vision-and-language navigation (VLN) is a trending topic which aims to navigate an intelligent agent to an expected position through natural language instructions. This work addresses the task of VLN from a previously-ignored aspect, namely the spatial route prior of the navigation scenes. A critically enabling innovation of this work is explicitly considering the spatial route prior under several different VLN settings. In a most information-rich case of knowing environment maps and admitting shortest-path prior, we observe that given an origin-destination node pair, the internal route can be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05728","kind":"arxiv","version":1},"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/2110.05728/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":"2110.05728","created_at":"2026-07-05T03:22:05.795159+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.05728v1","created_at":"2026-07-05T03:22:05.795159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05728","created_at":"2026-07-05T03:22:05.795159+00:00"},{"alias_kind":"pith_short_12","alias_value":"U56BILAPY22O","created_at":"2026-07-05T03:22:05.795159+00:00"},{"alias_kind":"pith_short_16","alias_value":"U56BILAPY22OBSPG","created_at":"2026-07-05T03:22:05.795159+00:00"},{"alias_kind":"pith_short_8","alias_value":"U56BILAP","created_at":"2026-07-05T03:22:05.795159+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.16516","citing_title":"Think Hierarchically, Act Dynamically: Hierarchical Multi-modal Fusion and Reasoning for Vision-and-Language Navigation","ref_index":68,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U56BILAPY22OBSPGM3GDH2WMC3","json":"https://pith.science/pith/U56BILAPY22OBSPGM3GDH2WMC3.json","graph_json":"https://pith.science/api/pith-number/U56BILAPY22OBSPGM3GDH2WMC3/graph.json","events_json":"https://pith.science/api/pith-number/U56BILAPY22OBSPGM3GDH2WMC3/events.json","paper":"https://pith.science/paper/U56BILAP"},"agent_actions":{"view_html":"https://pith.science/pith/U56BILAPY22OBSPGM3GDH2WMC3","download_json":"https://pith.science/pith/U56BILAPY22OBSPGM3GDH2WMC3.json","view_paper":"https://pith.science/paper/U56BILAP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.05728&json=true","fetch_graph":"https://pith.science/api/pith-number/U56BILAPY22OBSPGM3GDH2WMC3/graph.json","fetch_events":"https://pith.science/api/pith-number/U56BILAPY22OBSPGM3GDH2WMC3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U56BILAPY22OBSPGM3GDH2WMC3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U56BILAPY22OBSPGM3GDH2WMC3/action/storage_attestation","attest_author":"https://pith.science/pith/U56BILAPY22OBSPGM3GDH2WMC3/action/author_attestation","sign_citation":"https://pith.science/pith/U56BILAPY22OBSPGM3GDH2WMC3/action/citation_signature","submit_replication":"https://pith.science/pith/U56BILAPY22OBSPGM3GDH2WMC3/action/replication_record"}},"created_at":"2026-07-05T03:22:05.795159+00:00","updated_at":"2026-07-05T03:22:05.795159+00:00"}