{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MZZGOJFNC3A7IGRKIKZCJUQLS4","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":"391b701da0491b2b1662931e67797d75df321c6fbc716221b821e41373b3ced8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-12T14:40:50Z","title_canon_sha256":"42c4d03ce5cbb645be8b7e9d3654eed5e8fe45002f2ef4e976f936c20edf2357"},"schema_version":"1.0","source":{"id":"2506.10756","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.10756","created_at":"2026-07-05T11:20:29Z"},{"alias_kind":"arxiv_version","alias_value":"2506.10756v1","created_at":"2026-07-05T11:20:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10756","created_at":"2026-07-05T11:20:29Z"},{"alias_kind":"pith_short_12","alias_value":"MZZGOJFNC3A7","created_at":"2026-07-05T11:20:29Z"},{"alias_kind":"pith_short_16","alias_value":"MZZGOJFNC3A7IGRK","created_at":"2026-07-05T11:20:29Z"},{"alias_kind":"pith_short_8","alias_value":"MZZGOJFN","created_at":"2026-07-05T11:20:29Z"}],"graph_snapshots":[{"event_id":"sha256:cb904f066db0cefbd67ab04e70065665fe57ca8482567e54a784660e7f2e87f6","target":"graph","created_at":"2026-07-05T11:20:29Z","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/2506.10756/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haosheng Yu, Jiaping Xiao, Mir Feroskhan, Yuhang Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-12T14:40:50Z","title":"Grounded Vision-Language Navigation for UAVs with Open-Vocabulary Goal Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10756","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:c8e42153cb9589faa8dbf99b790085399aed5d0c91ad62ee3d24f6696864fc56","target":"record","created_at":"2026-07-05T11:20:29Z","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":"391b701da0491b2b1662931e67797d75df321c6fbc716221b821e41373b3ced8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-12T14:40:50Z","title_canon_sha256":"42c4d03ce5cbb645be8b7e9d3654eed5e8fe45002f2ef4e976f936c20edf2357"},"schema_version":"1.0","source":{"id":"2506.10756","kind":"arxiv","version":1}},"canonical_sha256":"66726724ad16c1f41a2a42b224d20b9734f218ed33ab61a78e39586ad8962834","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66726724ad16c1f41a2a42b224d20b9734f218ed33ab61a78e39586ad8962834","first_computed_at":"2026-07-05T11:20:29.948017Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:29.948017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z5BaDqib/2VJ6H1cMHUyoOgZGe6x+GTEfcuFOQahf+ob/IEeUX4YZ59GTwwu8ZZfH9ZCKOfwnQvD6rnfVXtkCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:29.948560Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.10756","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8e42153cb9589faa8dbf99b790085399aed5d0c91ad62ee3d24f6696864fc56","sha256:cb904f066db0cefbd67ab04e70065665fe57ca8482567e54a784660e7f2e87f6"],"state_sha256":"6ec19b7518bdbe710e4d1fb0fd87011451e0017e75e80517f4b85dc5e47dc703"}