{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FBEI6GWDQSV2PDTQX5HLYTVKO7","short_pith_number":"pith:FBEI6GWD","schema_version":"1.0","canonical_sha256":"28488f1ac384aba78e70bf4ebc4eaa77cba1f45beccc22d676b0b4e18c93aa30","source":{"kind":"arxiv","id":"2203.13838","version":1},"attestation_state":"computed","paper":{"title":"Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areas","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Raphael Schumann, Stefan Riezler","submitted_at":"2022-03-25T18:06:14Z","abstract_excerpt":"Vision and language navigation (VLN) is a challenging visually-grounded language understanding task. Given a natural language navigation instruction, a visual agent interacts with a graph-based environment equipped with panorama images and tries to follow the described route. Most prior work has been conducted in indoor scenarios where best results were obtained for navigation on routes that are similar to the training routes, with sharp drops in performance when testing on unseen environments. We focus on VLN in outdoor scenarios and find that in contrast to indoor VLN, most of the gain in ou"},"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":"2203.13838","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-25T18:06:14Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"7e8d40ca95395cd89d16c7fb2355bda9e08543832244fbdf139adb9a78ee173b","abstract_canon_sha256":"a9741e259c99d8458205e0bf4183c946802ae8729df7af6f04942a50756ef8db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:44.037456Z","signature_b64":"z1E+YzRkRDIJxWxg3mrMIlZEEylH98qPLOjK2Pz5AQIjFJ9723vcP9sD/KEjXy6gkpZNO+8Gl+50Y4A0jhyGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28488f1ac384aba78e70bf4ebc4eaa77cba1f45beccc22d676b0b4e18c93aa30","last_reissued_at":"2026-07-05T04:08:44.037032Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:44.037032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areas","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Raphael Schumann, Stefan Riezler","submitted_at":"2022-03-25T18:06:14Z","abstract_excerpt":"Vision and language navigation (VLN) is a challenging visually-grounded language understanding task. Given a natural language navigation instruction, a visual agent interacts with a graph-based environment equipped with panorama images and tries to follow the described route. Most prior work has been conducted in indoor scenarios where best results were obtained for navigation on routes that are similar to the training routes, with sharp drops in performance when testing on unseen environments. We focus on VLN in outdoor scenarios and find that in contrast to indoor VLN, most of the gain in ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13838","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/2203.13838/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":"2203.13838","created_at":"2026-07-05T04:08:44.037100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.13838v1","created_at":"2026-07-05T04:08:44.037100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13838","created_at":"2026-07-05T04:08:44.037100+00:00"},{"alias_kind":"pith_short_12","alias_value":"FBEI6GWDQSV2","created_at":"2026-07-05T04:08:44.037100+00:00"},{"alias_kind":"pith_short_16","alias_value":"FBEI6GWDQSV2PDTQ","created_at":"2026-07-05T04:08:44.037100+00:00"},{"alias_kind":"pith_short_8","alias_value":"FBEI6GWD","created_at":"2026-07-05T04:08:44.037100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.08579","citing_title":"NavAgent: Multi-scale Urban Street View Fusion For UAV Embodied Vision-and-Language Navigation","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FBEI6GWDQSV2PDTQX5HLYTVKO7","json":"https://pith.science/pith/FBEI6GWDQSV2PDTQX5HLYTVKO7.json","graph_json":"https://pith.science/api/pith-number/FBEI6GWDQSV2PDTQX5HLYTVKO7/graph.json","events_json":"https://pith.science/api/pith-number/FBEI6GWDQSV2PDTQX5HLYTVKO7/events.json","paper":"https://pith.science/paper/FBEI6GWD"},"agent_actions":{"view_html":"https://pith.science/pith/FBEI6GWDQSV2PDTQX5HLYTVKO7","download_json":"https://pith.science/pith/FBEI6GWDQSV2PDTQX5HLYTVKO7.json","view_paper":"https://pith.science/paper/FBEI6GWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.13838&json=true","fetch_graph":"https://pith.science/api/pith-number/FBEI6GWDQSV2PDTQX5HLYTVKO7/graph.json","fetch_events":"https://pith.science/api/pith-number/FBEI6GWDQSV2PDTQX5HLYTVKO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FBEI6GWDQSV2PDTQX5HLYTVKO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FBEI6GWDQSV2PDTQX5HLYTVKO7/action/storage_attestation","attest_author":"https://pith.science/pith/FBEI6GWDQSV2PDTQX5HLYTVKO7/action/author_attestation","sign_citation":"https://pith.science/pith/FBEI6GWDQSV2PDTQX5HLYTVKO7/action/citation_signature","submit_replication":"https://pith.science/pith/FBEI6GWDQSV2PDTQX5HLYTVKO7/action/replication_record"}},"created_at":"2026-07-05T04:08:44.037100+00:00","updated_at":"2026-07-05T04:08:44.037100+00:00"}