{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FG55UZ7JAKVCBNDNVTSAYJJE47","short_pith_number":"pith:FG55UZ7J","schema_version":"1.0","canonical_sha256":"29bbda67e902aa20b46dace40c2524e7e93f34a7b68337a56454ea7377651364","source":{"kind":"arxiv","id":"2308.06735","version":1},"attestation_state":"computed","paper":{"title":"AerialVLN: Vision-and-Language Navigation for UAVs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Hongsheng Zhang, Peng Wang, Qi Wu, Shubo Liu, Yaning Zhang, Yuankai Qi","submitted_at":"2023-08-13T09:55:04Z","abstract_excerpt":"Recently emerged Vision-and-Language Navigation (VLN) tasks have drawn significant attention in both computer vision and natural language processing communities. Existing VLN tasks are built for agents that navigate on the ground, either indoors or outdoors. However, many tasks require intelligent agents to carry out in the sky, such as UAV-based goods delivery, traffic/security patrol, and scenery tour, to name a few. Navigating in the sky is more complicated than on the ground because agents need to consider the flying height and more complex spatial relationship reasoning. To fill this gap "},"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":"2308.06735","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-13T09:55:04Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"8d1682675b624775721cbbc0fb5674881e41e13c6c5b0dbc0ac4af774ab842a6","abstract_canon_sha256":"ba3567eeed408d02ad23c56e865d038a7f32fccf4927194305d163d232b0d127"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:44.457993Z","signature_b64":"+IQhtVZQvqXDcOzdsH8/WcqXewTbJCxcz+4YAIR78bQMbjiELzQ3Scy3OHqEdglzxnap3gS3KOg0cxt+48+8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29bbda67e902aa20b46dace40c2524e7e93f34a7b68337a56454ea7377651364","last_reissued_at":"2026-07-05T06:40:44.457622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:44.457622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AerialVLN: Vision-and-Language Navigation for UAVs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Hongsheng Zhang, Peng Wang, Qi Wu, Shubo Liu, Yaning Zhang, Yuankai Qi","submitted_at":"2023-08-13T09:55:04Z","abstract_excerpt":"Recently emerged Vision-and-Language Navigation (VLN) tasks have drawn significant attention in both computer vision and natural language processing communities. Existing VLN tasks are built for agents that navigate on the ground, either indoors or outdoors. However, many tasks require intelligent agents to carry out in the sky, such as UAV-based goods delivery, traffic/security patrol, and scenery tour, to name a few. Navigating in the sky is more complicated than on the ground because agents need to consider the flying height and more complex spatial relationship reasoning. To fill this gap "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06735","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/2308.06735/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":"2308.06735","created_at":"2026-07-05T06:40:44.457668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.06735v1","created_at":"2026-07-05T06:40:44.457668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06735","created_at":"2026-07-05T06:40:44.457668+00:00"},{"alias_kind":"pith_short_12","alias_value":"FG55UZ7JAKVC","created_at":"2026-07-05T06:40:44.457668+00:00"},{"alias_kind":"pith_short_16","alias_value":"FG55UZ7JAKVCBNDN","created_at":"2026-07-05T06:40:44.457668+00:00"},{"alias_kind":"pith_short_8","alias_value":"FG55UZ7J","created_at":"2026-07-05T06:40:44.457668+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07509","citing_title":"Taking Flight with Dialogue: Enabling Natural Language Control for PX4-based Drone Agent","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FG55UZ7JAKVCBNDNVTSAYJJE47","json":"https://pith.science/pith/FG55UZ7JAKVCBNDNVTSAYJJE47.json","graph_json":"https://pith.science/api/pith-number/FG55UZ7JAKVCBNDNVTSAYJJE47/graph.json","events_json":"https://pith.science/api/pith-number/FG55UZ7JAKVCBNDNVTSAYJJE47/events.json","paper":"https://pith.science/paper/FG55UZ7J"},"agent_actions":{"view_html":"https://pith.science/pith/FG55UZ7JAKVCBNDNVTSAYJJE47","download_json":"https://pith.science/pith/FG55UZ7JAKVCBNDNVTSAYJJE47.json","view_paper":"https://pith.science/paper/FG55UZ7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.06735&json=true","fetch_graph":"https://pith.science/api/pith-number/FG55UZ7JAKVCBNDNVTSAYJJE47/graph.json","fetch_events":"https://pith.science/api/pith-number/FG55UZ7JAKVCBNDNVTSAYJJE47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FG55UZ7JAKVCBNDNVTSAYJJE47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FG55UZ7JAKVCBNDNVTSAYJJE47/action/storage_attestation","attest_author":"https://pith.science/pith/FG55UZ7JAKVCBNDNVTSAYJJE47/action/author_attestation","sign_citation":"https://pith.science/pith/FG55UZ7JAKVCBNDNVTSAYJJE47/action/citation_signature","submit_replication":"https://pith.science/pith/FG55UZ7JAKVCBNDNVTSAYJJE47/action/replication_record"}},"created_at":"2026-07-05T06:40:44.457668+00:00","updated_at":"2026-07-05T06:40:44.457668+00:00"}