{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZOUQKLTIXNRJND6EZMDFYY6AXS","short_pith_number":"pith:ZOUQKLTI","schema_version":"1.0","canonical_sha256":"cba9052e68bb62968fc4cb065c63c0bcbaf0b6c1686d44b62ad2c761bca41771","source":{"kind":"arxiv","id":"2505.12835","version":1},"attestation_state":"computed","paper":{"title":"FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Agachai Sumalee, Haidong Wang, Hengxing Cai, Jingcheng Deng, Jingjun Tan, Jinhan Dong, Renxin Zhong, Sihang Li, Zhifeng Gao, Zicheng Su","submitted_at":"2025-05-19T08:21:20Z","abstract_excerpt":"Unmanned Aerial Vehicle (UAV) Vision-and-Language Navigation (VLN) is vital for applications such as disaster response, logistics delivery, and urban inspection. However, existing methods often struggle with insufficient multimodal fusion, weak generalization, and poor interpretability. To address these challenges, we propose FlightGPT, a novel UAV VLN framework built upon Vision-Language Models (VLMs) with powerful multimodal perception capabilities. We design a two-stage training pipeline: first, Supervised Fine-Tuning (SFT) using high-quality demonstrations to improve initialization and str"},"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":"2505.12835","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T08:21:20Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"19a0418adebcdecf03ab22a85e7e35bb593228ec3adb0d40202e5a9e40c35071","abstract_canon_sha256":"615ca2be9f0af6862efc2963fc3c1306666dffe16969ca5fcf06527f447d5dd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:10.417818Z","signature_b64":"s0yS9UiWADpGwfq/0Obxv9Y0hx/DG7ohISmxCL7dM0wNVnSJ632ELSof0PkS8Z7c9OGwzmnlB6uP/odF7//HDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cba9052e68bb62968fc4cb065c63c0bcbaf0b6c1686d44b62ad2c761bca41771","last_reissued_at":"2026-07-05T11:05:10.417308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:10.417308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Agachai Sumalee, Haidong Wang, Hengxing Cai, Jingcheng Deng, Jingjun Tan, Jinhan Dong, Renxin Zhong, Sihang Li, Zhifeng Gao, Zicheng Su","submitted_at":"2025-05-19T08:21:20Z","abstract_excerpt":"Unmanned Aerial Vehicle (UAV) Vision-and-Language Navigation (VLN) is vital for applications such as disaster response, logistics delivery, and urban inspection. However, existing methods often struggle with insufficient multimodal fusion, weak generalization, and poor interpretability. To address these challenges, we propose FlightGPT, a novel UAV VLN framework built upon Vision-Language Models (VLMs) with powerful multimodal perception capabilities. We design a two-stage training pipeline: first, Supervised Fine-Tuning (SFT) using high-quality demonstrations to improve initialization and str"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12835","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/2505.12835/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":"2505.12835","created_at":"2026-07-05T11:05:10.417388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12835v1","created_at":"2026-07-05T11:05:10.417388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12835","created_at":"2026-07-05T11:05:10.417388+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZOUQKLTIXNRJ","created_at":"2026-07-05T11:05:10.417388+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZOUQKLTIXNRJND6E","created_at":"2026-07-05T11:05:10.417388+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZOUQKLTI","created_at":"2026-07-05T11:05:10.417388+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20045","citing_title":"See-and-Reach: Precise Vision-Language Navigation for UAVs within the Field of View","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31654","citing_title":"DynFly: Dynamic-Aware Continuous Trajectory Generation for UAV Vision-Language Navigation in Urban Environments","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31654","citing_title":"DynFly: Dynamic-Aware Continuous Trajectory Generation for UAV Vision-Language Navigation in Urban Environments","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11183","citing_title":"Mitigating Error Accumulation in Continuous Navigation via Memory-Augmented Kalman Filtering","ref_index":1,"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":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZOUQKLTIXNRJND6EZMDFYY6AXS","json":"https://pith.science/pith/ZOUQKLTIXNRJND6EZMDFYY6AXS.json","graph_json":"https://pith.science/api/pith-number/ZOUQKLTIXNRJND6EZMDFYY6AXS/graph.json","events_json":"https://pith.science/api/pith-number/ZOUQKLTIXNRJND6EZMDFYY6AXS/events.json","paper":"https://pith.science/paper/ZOUQKLTI"},"agent_actions":{"view_html":"https://pith.science/pith/ZOUQKLTIXNRJND6EZMDFYY6AXS","download_json":"https://pith.science/pith/ZOUQKLTIXNRJND6EZMDFYY6AXS.json","view_paper":"https://pith.science/paper/ZOUQKLTI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12835&json=true","fetch_graph":"https://pith.science/api/pith-number/ZOUQKLTIXNRJND6EZMDFYY6AXS/graph.json","fetch_events":"https://pith.science/api/pith-number/ZOUQKLTIXNRJND6EZMDFYY6AXS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZOUQKLTIXNRJND6EZMDFYY6AXS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZOUQKLTIXNRJND6EZMDFYY6AXS/action/storage_attestation","attest_author":"https://pith.science/pith/ZOUQKLTIXNRJND6EZMDFYY6AXS/action/author_attestation","sign_citation":"https://pith.science/pith/ZOUQKLTIXNRJND6EZMDFYY6AXS/action/citation_signature","submit_replication":"https://pith.science/pith/ZOUQKLTIXNRJND6EZMDFYY6AXS/action/replication_record"}},"created_at":"2026-07-05T11:05:10.417388+00:00","updated_at":"2026-07-05T11:05:10.417388+00:00"}