{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZOUQKLTIXNRJND6EZMDFYY6AXS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"615ca2be9f0af6862efc2963fc3c1306666dffe16969ca5fcf06527f447d5dd9","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T08:21:20Z","title_canon_sha256":"19a0418adebcdecf03ab22a85e7e35bb593228ec3adb0d40202e5a9e40c35071"},"schema_version":"1.0","source":{"id":"2505.12835","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12835","created_at":"2026-07-05T11:05:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12835v1","created_at":"2026-07-05T11:05:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12835","created_at":"2026-07-05T11:05:10Z"},{"alias_kind":"pith_short_12","alias_value":"ZOUQKLTIXNRJ","created_at":"2026-07-05T11:05:10Z"},{"alias_kind":"pith_short_16","alias_value":"ZOUQKLTIXNRJND6E","created_at":"2026-07-05T11:05:10Z"},{"alias_kind":"pith_short_8","alias_value":"ZOUQKLTI","created_at":"2026-07-05T11:05:10Z"}],"graph_snapshots":[{"event_id":"sha256:d1c7afc3a965880a70de3fbaa305c7b5351f2f47c6ca2c9821a6089fcd6a94e3","target":"graph","created_at":"2026-07-05T11:05:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.12835/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Agachai Sumalee, Haidong Wang, Hengxing Cai, Jingcheng Deng, Jingjun Tan, Jinhan Dong, Renxin Zhong, Sihang Li, Zhifeng Gao, Zicheng Su","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T08:21:20Z","title":"FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12835","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2c023ebab3168a3df6ef1efa5166fd17784567734311d6509dd4aeaf07d036eb","target":"record","created_at":"2026-07-05T11:05:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"615ca2be9f0af6862efc2963fc3c1306666dffe16969ca5fcf06527f447d5dd9","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T08:21:20Z","title_canon_sha256":"19a0418adebcdecf03ab22a85e7e35bb593228ec3adb0d40202e5a9e40c35071"},"schema_version":"1.0","source":{"id":"2505.12835","kind":"arxiv","version":1}},"canonical_sha256":"cba9052e68bb62968fc4cb065c63c0bcbaf0b6c1686d44b62ad2c761bca41771","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cba9052e68bb62968fc4cb065c63c0bcbaf0b6c1686d44b62ad2c761bca41771","first_computed_at":"2026-07-05T11:05:10.417308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:10.417308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s0yS9UiWADpGwfq/0Obxv9Y0hx/DG7ohISmxCL7dM0wNVnSJ632ELSof0PkS8Z7c9OGwzmnlB6uP/odF7//HDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:10.417818Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12835","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c023ebab3168a3df6ef1efa5166fd17784567734311d6509dd4aeaf07d036eb","sha256:d1c7afc3a965880a70de3fbaa305c7b5351f2f47c6ca2c9821a6089fcd6a94e3"],"state_sha256":"d20bf22f3bd9d4e129e5f7bef38bbe8af4bc71743b73c2e74c629c705e4b4ecc"}