{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5W4G55OHJNAJCOCKLBQHIDLCTI","short_pith_number":"pith:5W4G55OH","schema_version":"1.0","canonical_sha256":"edb86ef5c74b4091384a5860740d629a077ecf0b1c7829311df94dfce54d6a5c","source":{"kind":"arxiv","id":"2010.07954","version":1},"attestation_state":"computed","paper":{"title":"Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Alexander Ku, Eugene Ie, Jason Baldridge, Peter Anderson, Roma Patel","submitted_at":"2020-10-15T18:01:15Z","abstract_excerpt":"We introduce Room-Across-Room (RxR), a new Vision-and-Language Navigation (VLN) dataset. RxR is multilingual (English, Hindi, and Telugu) and larger (more paths and instructions) than other VLN datasets. It emphasizes the role of language in VLN by addressing known biases in paths and eliciting more references to visible entities. Furthermore, each word in an instruction is time-aligned to the virtual poses of instruction creators and validators. We establish baseline scores for monolingual and multilingual settings and multitask learning when including Room-to-Room annotations. We also provid"},"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":"2010.07954","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-15T18:01:15Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"21a661a6ec92978fa2d328ed29577874b62ff043d21e3ca41cca747d188504d6","abstract_canon_sha256":"d29efd520c017e81a7451dcb696a42640f57f4bde7d57cb6754a58d54976e888"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:29.545055Z","signature_b64":"h+zcZHJoLzPRKPLZBj6rQ8913ixSCjG4WHzjvxZDhQRTseA25njg1JvpYObuvPCTkFU5uIpmIfMd8xY8d+jECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edb86ef5c74b4091384a5860740d629a077ecf0b1c7829311df94dfce54d6a5c","last_reissued_at":"2026-07-05T01:43:29.544569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:29.544569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Alexander Ku, Eugene Ie, Jason Baldridge, Peter Anderson, Roma Patel","submitted_at":"2020-10-15T18:01:15Z","abstract_excerpt":"We introduce Room-Across-Room (RxR), a new Vision-and-Language Navigation (VLN) dataset. RxR is multilingual (English, Hindi, and Telugu) and larger (more paths and instructions) than other VLN datasets. It emphasizes the role of language in VLN by addressing known biases in paths and eliciting more references to visible entities. Furthermore, each word in an instruction is time-aligned to the virtual poses of instruction creators and validators. We establish baseline scores for monolingual and multilingual settings and multitask learning when including Room-to-Room annotations. We also provid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07954","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/2010.07954/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":"2010.07954","created_at":"2026-07-05T01:43:29.544628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.07954v1","created_at":"2026-07-05T01:43:29.544628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07954","created_at":"2026-07-05T01:43:29.544628+00:00"},{"alias_kind":"pith_short_12","alias_value":"5W4G55OHJNAJ","created_at":"2026-07-05T01:43:29.544628+00:00"},{"alias_kind":"pith_short_16","alias_value":"5W4G55OHJNAJCOCK","created_at":"2026-07-05T01:43:29.544628+00:00"},{"alias_kind":"pith_short_8","alias_value":"5W4G55OH","created_at":"2026-07-05T01:43:29.544628+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22424","citing_title":"FlowDec: Temporal Conditional Flow Decorruptor for Robust Continuous Vision-Language Navigation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30367","citing_title":"FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22036","citing_title":"GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17097","citing_title":"Progress-Think: Semantic Progress Reasoning for Vision-Language Navigation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2512.21714","citing_title":"AstraNav-World: World Model for Foresight Control and Consistency","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2109.08238","citing_title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11762","citing_title":"NavOL: Navigation Policy with Online Imitation Learning","ref_index":7,"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":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09441","citing_title":"Beyond Isolation: A Unified Benchmark for General-Purpose Navigation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17473","citing_title":"Dual-Anchoring: Addressing State Drift in Vision-Language Navigation","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17407","citing_title":"Think before Go: Hierarchical Reasoning for Image-goal Navigation","ref_index":101,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5W4G55OHJNAJCOCKLBQHIDLCTI","json":"https://pith.science/pith/5W4G55OHJNAJCOCKLBQHIDLCTI.json","graph_json":"https://pith.science/api/pith-number/5W4G55OHJNAJCOCKLBQHIDLCTI/graph.json","events_json":"https://pith.science/api/pith-number/5W4G55OHJNAJCOCKLBQHIDLCTI/events.json","paper":"https://pith.science/paper/5W4G55OH"},"agent_actions":{"view_html":"https://pith.science/pith/5W4G55OHJNAJCOCKLBQHIDLCTI","download_json":"https://pith.science/pith/5W4G55OHJNAJCOCKLBQHIDLCTI.json","view_paper":"https://pith.science/paper/5W4G55OH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.07954&json=true","fetch_graph":"https://pith.science/api/pith-number/5W4G55OHJNAJCOCKLBQHIDLCTI/graph.json","fetch_events":"https://pith.science/api/pith-number/5W4G55OHJNAJCOCKLBQHIDLCTI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5W4G55OHJNAJCOCKLBQHIDLCTI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5W4G55OHJNAJCOCKLBQHIDLCTI/action/storage_attestation","attest_author":"https://pith.science/pith/5W4G55OHJNAJCOCKLBQHIDLCTI/action/author_attestation","sign_citation":"https://pith.science/pith/5W4G55OHJNAJCOCKLBQHIDLCTI/action/citation_signature","submit_replication":"https://pith.science/pith/5W4G55OHJNAJCOCKLBQHIDLCTI/action/replication_record"}},"created_at":"2026-07-05T01:43:29.544628+00:00","updated_at":"2026-07-05T01:43:29.544628+00:00"}