{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MZZGOJFNC3A7IGRKIKZCJUQLS4","short_pith_number":"pith:MZZGOJFN","schema_version":"1.0","canonical_sha256":"66726724ad16c1f41a2a42b224d20b9734f218ed33ab61a78e39586ad8962834","source":{"kind":"arxiv","id":"2506.10756","version":1},"attestation_state":"computed","paper":{"title":"Grounded Vision-Language Navigation for UAVs with Open-Vocabulary Goal Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Haosheng Yu, Jiaping Xiao, Mir Feroskhan, Yuhang Zhang","submitted_at":"2025-06-12T14:40:50Z","abstract_excerpt":"Vision-and-language navigation (VLN) is a long-standing challenge in autonomous robotics, aiming to empower agents with the ability to follow human instructions while navigating complex environments. Two key bottlenecks remain in this field: generalization to out-of-distribution environments and reliance on fixed discrete action spaces. To address these challenges, we propose Vision-Language Fly (VLFly), a framework tailored for Unmanned Aerial Vehicles (UAVs) to execute language-guided flight. Without the requirement for localization or active ranging sensors, VLFly outputs continuous velocit"},"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":"2506.10756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-12T14:40:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"42c4d03ce5cbb645be8b7e9d3654eed5e8fe45002f2ef4e976f936c20edf2357","abstract_canon_sha256":"391b701da0491b2b1662931e67797d75df321c6fbc716221b821e41373b3ced8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:29.948560Z","signature_b64":"z5BaDqib/2VJ6H1cMHUyoOgZGe6x+GTEfcuFOQahf+ob/IEeUX4YZ59GTwwu8ZZfH9ZCKOfwnQvD6rnfVXtkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66726724ad16c1f41a2a42b224d20b9734f218ed33ab61a78e39586ad8962834","last_reissued_at":"2026-07-05T11:20:29.948017Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:29.948017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounded Vision-Language Navigation for UAVs with Open-Vocabulary Goal Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Haosheng Yu, Jiaping Xiao, Mir Feroskhan, Yuhang Zhang","submitted_at":"2025-06-12T14:40:50Z","abstract_excerpt":"Vision-and-language navigation (VLN) is a long-standing challenge in autonomous robotics, aiming to empower agents with the ability to follow human instructions while navigating complex environments. Two key bottlenecks remain in this field: generalization to out-of-distribution environments and reliance on fixed discrete action spaces. To address these challenges, we propose Vision-Language Fly (VLFly), a framework tailored for Unmanned Aerial Vehicles (UAVs) to execute language-guided flight. Without the requirement for localization or active ranging sensors, VLFly outputs continuous velocit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10756","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/2506.10756/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":"2506.10756","created_at":"2026-07-05T11:20:29.948079+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10756v1","created_at":"2026-07-05T11:20:29.948079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10756","created_at":"2026-07-05T11:20:29.948079+00:00"},{"alias_kind":"pith_short_12","alias_value":"MZZGOJFNC3A7","created_at":"2026-07-05T11:20:29.948079+00:00"},{"alias_kind":"pith_short_16","alias_value":"MZZGOJFNC3A7IGRK","created_at":"2026-07-05T11:20:29.948079+00:00"},{"alias_kind":"pith_short_8","alias_value":"MZZGOJFN","created_at":"2026-07-05T11:20:29.948079+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08359","citing_title":"FSD-VLN: Fast-Slow Dual-System Modeling for Aerial Long-Horizon Vision-Language Navigation","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20045","citing_title":"See-and-Reach: Precise Vision-Language Navigation for UAVs within the Field of View","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13654","citing_title":"Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap","ref_index":246,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07705","citing_title":"Vision-Language Navigation for Aerial Robots: Towards the Era of Large Language Models","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05062","citing_title":"GaussFly: Contrastive Reinforcement Learning for Visuomotor Policies in 3D Gaussian Fields","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16298","citing_title":"FineCog-Nav: Integrating Fine-grained Cognitive Modules for Zero-shot Multimodal UAV Navigation","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MZZGOJFNC3A7IGRKIKZCJUQLS4","json":"https://pith.science/pith/MZZGOJFNC3A7IGRKIKZCJUQLS4.json","graph_json":"https://pith.science/api/pith-number/MZZGOJFNC3A7IGRKIKZCJUQLS4/graph.json","events_json":"https://pith.science/api/pith-number/MZZGOJFNC3A7IGRKIKZCJUQLS4/events.json","paper":"https://pith.science/paper/MZZGOJFN"},"agent_actions":{"view_html":"https://pith.science/pith/MZZGOJFNC3A7IGRKIKZCJUQLS4","download_json":"https://pith.science/pith/MZZGOJFNC3A7IGRKIKZCJUQLS4.json","view_paper":"https://pith.science/paper/MZZGOJFN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10756&json=true","fetch_graph":"https://pith.science/api/pith-number/MZZGOJFNC3A7IGRKIKZCJUQLS4/graph.json","fetch_events":"https://pith.science/api/pith-number/MZZGOJFNC3A7IGRKIKZCJUQLS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MZZGOJFNC3A7IGRKIKZCJUQLS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MZZGOJFNC3A7IGRKIKZCJUQLS4/action/storage_attestation","attest_author":"https://pith.science/pith/MZZGOJFNC3A7IGRKIKZCJUQLS4/action/author_attestation","sign_citation":"https://pith.science/pith/MZZGOJFNC3A7IGRKIKZCJUQLS4/action/citation_signature","submit_replication":"https://pith.science/pith/MZZGOJFNC3A7IGRKIKZCJUQLS4/action/replication_record"}},"created_at":"2026-07-05T11:20:29.948079+00:00","updated_at":"2026-07-05T11:20:29.948079+00:00"}