{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MF5SNKCYQWRMJRKTAJ2ZUUBFNW","short_pith_number":"pith:MF5SNKCY","schema_version":"1.0","canonical_sha256":"617b26a85885a2c4c55302759a50256d8194d2d9b6fc84b8521a555512ef45ea","source":{"kind":"arxiv","id":"2601.03707","version":2},"attestation_state":"computed","paper":{"title":"AirNav: A Large-Scale UAV Vision-and-Language Navigation Dataset with Natural and Diverse Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changhao Nai, Hengxing Cai, Jingjun Tan, Jinhan Dong, Jue Hou, Ligang Huang, Renxin Zhong, Wenhao Lu, Yijie Rao, Zanyang Zhong","submitted_at":"2026-01-07T08:46:09Z","abstract_excerpt":"Existing UAV vision-and-language navigation (VLN) benchmarks rarely provide realistic aerial scenes, natural process-level instructions, and sufficient scale simultaneously, making it difficult to systematically train and evaluate UAV VLN agents under realistic settings. To address this, we propose \\textbf{AirNav}, a large-scale benchmark built on real urban aerial data, comprising 137K navigation samples with natural and diverse instructions generated via a human--LLM collaborative pipeline with 10 user personas. We conduct a systematic evaluation of representative approaches on AirNav, rangi"},"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":"2601.03707","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-07T08:46:09Z","cross_cats_sorted":[],"title_canon_sha256":"99b446d84439604f560207b28d88f60f9327e3f51d73f411de94b01a1efef013","abstract_canon_sha256":"b5a78abb393f695949d3cd71c2fba011c5ceb307ce31eb6b13119dfcc12c4ea9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:31.777625Z","signature_b64":"GJJduL5lZsQaRpbQfpHl+uKak0X60SIvvdHJmoBNF2kabeysUPVUVo2x1dLym5Zwnlv+3ytmFlRu1o1eOTDiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"617b26a85885a2c4c55302759a50256d8194d2d9b6fc84b8521a555512ef45ea","last_reissued_at":"2026-05-20T00:00:31.777055Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:31.777055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AirNav: A Large-Scale UAV Vision-and-Language Navigation Dataset with Natural and Diverse Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changhao Nai, Hengxing Cai, Jingjun Tan, Jinhan Dong, Jue Hou, Ligang Huang, Renxin Zhong, Wenhao Lu, Yijie Rao, Zanyang Zhong","submitted_at":"2026-01-07T08:46:09Z","abstract_excerpt":"Existing UAV vision-and-language navigation (VLN) benchmarks rarely provide realistic aerial scenes, natural process-level instructions, and sufficient scale simultaneously, making it difficult to systematically train and evaluate UAV VLN agents under realistic settings. To address this, we propose \\textbf{AirNav}, a large-scale benchmark built on real urban aerial data, comprising 137K navigation samples with natural and diverse instructions generated via a human--LLM collaborative pipeline with 10 user personas. We conduct a systematic evaluation of representative approaches on AirNav, rangi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.03707","kind":"arxiv","version":2},"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/2601.03707/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":"2601.03707","created_at":"2026-05-20T00:00:31.777143+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.03707v2","created_at":"2026-05-20T00:00:31.777143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.03707","created_at":"2026-05-20T00:00:31.777143+00:00"},{"alias_kind":"pith_short_12","alias_value":"MF5SNKCYQWRM","created_at":"2026-05-20T00:00:31.777143+00:00"},{"alias_kind":"pith_short_16","alias_value":"MF5SNKCYQWRMJRKT","created_at":"2026-05-20T00:00:31.777143+00:00"},{"alias_kind":"pith_short_8","alias_value":"MF5SNKCY","created_at":"2026-05-20T00:00:31.777143+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.07705","citing_title":"Vision-Language Navigation for Aerial Robots: Towards the Era of Large Language Models","ref_index":112,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MF5SNKCYQWRMJRKTAJ2ZUUBFNW","json":"https://pith.science/pith/MF5SNKCYQWRMJRKTAJ2ZUUBFNW.json","graph_json":"https://pith.science/api/pith-number/MF5SNKCYQWRMJRKTAJ2ZUUBFNW/graph.json","events_json":"https://pith.science/api/pith-number/MF5SNKCYQWRMJRKTAJ2ZUUBFNW/events.json","paper":"https://pith.science/paper/MF5SNKCY"},"agent_actions":{"view_html":"https://pith.science/pith/MF5SNKCYQWRMJRKTAJ2ZUUBFNW","download_json":"https://pith.science/pith/MF5SNKCYQWRMJRKTAJ2ZUUBFNW.json","view_paper":"https://pith.science/paper/MF5SNKCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.03707&json=true","fetch_graph":"https://pith.science/api/pith-number/MF5SNKCYQWRMJRKTAJ2ZUUBFNW/graph.json","fetch_events":"https://pith.science/api/pith-number/MF5SNKCYQWRMJRKTAJ2ZUUBFNW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MF5SNKCYQWRMJRKTAJ2ZUUBFNW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MF5SNKCYQWRMJRKTAJ2ZUUBFNW/action/storage_attestation","attest_author":"https://pith.science/pith/MF5SNKCYQWRMJRKTAJ2ZUUBFNW/action/author_attestation","sign_citation":"https://pith.science/pith/MF5SNKCYQWRMJRKTAJ2ZUUBFNW/action/citation_signature","submit_replication":"https://pith.science/pith/MF5SNKCYQWRMJRKTAJ2ZUUBFNW/action/replication_record"}},"created_at":"2026-05-20T00:00:31.777143+00:00","updated_at":"2026-05-20T00:00:31.777143+00:00"}