{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VZBENNHMITN7CRGRYNXMSXVARP","short_pith_number":"pith:VZBENNHM","schema_version":"1.0","canonical_sha256":"ae4246b4ec44dbf144d1c36ec95ea08beac9254f354e7eea9d83fbbd2e27aec1","source":{"kind":"arxiv","id":"2608.09564","version":1},"attestation_state":"computed","paper":{"title":"From Semantic Grounding to Decision Optimization: A Unified Framework for Long-Horizon UAV Vision-Language Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Di Huang, Jiaxin Chen, Zeyuan Ma","submitted_at":"2026-08-10T12:59:50Z","abstract_excerpt":"UAV vision-language navigation (UAV-VLN) focuses on enabling an aerial agent to follow natural-language instructions in open 3D environments from egocentric visual observations. Current approaches suffer from three coupled issues: weak grounding of instruction-relevant landmarks in visual observations, insufficient exploitation of long-horizon history, and unstable decisions under local traps or repeated exploration. To address these issues, we propose a unified semantic-to-decision framework. First, we present an instruction-grounded semantic enhancement module that injects object-level seman"},"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":"2608.09564","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T12:59:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5ac181446addfe15e682f516f08808c0e6ad8b1fd08ecc5d3b076eb6348dff36","abstract_canon_sha256":"e18fb50062cd40c2af158ac5da7e4ef6fe605b611302c9f350bd3510a55362e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:24:30.860413Z","signature_b64":"Sc/947m9psNCVkg7b+nN9tg+zXJgiVqgYJf5EFzhwZlhele3mp0NAIP/1wk/QC7ToZ9LDdJEyuDUjOyDeeVRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae4246b4ec44dbf144d1c36ec95ea08beac9254f354e7eea9d83fbbd2e27aec1","last_reissued_at":"2026-08-11T02:24:30.858822Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:24:30.858822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Semantic Grounding to Decision Optimization: A Unified Framework for Long-Horizon UAV Vision-Language Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Di Huang, Jiaxin Chen, Zeyuan Ma","submitted_at":"2026-08-10T12:59:50Z","abstract_excerpt":"UAV vision-language navigation (UAV-VLN) focuses on enabling an aerial agent to follow natural-language instructions in open 3D environments from egocentric visual observations. Current approaches suffer from three coupled issues: weak grounding of instruction-relevant landmarks in visual observations, insufficient exploitation of long-horizon history, and unstable decisions under local traps or repeated exploration. To address these issues, we propose a unified semantic-to-decision framework. First, we present an instruction-grounded semantic enhancement module that injects object-level seman"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09564","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/2608.09564/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":"2608.09564","created_at":"2026-08-11T02:24:30.859449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.09564v1","created_at":"2026-08-11T02:24:30.859449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09564","created_at":"2026-08-11T02:24:30.859449+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZBENNHMITN7","created_at":"2026-08-11T02:24:30.859449+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZBENNHMITN7CRGR","created_at":"2026-08-11T02:24:30.859449+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZBENNHM","created_at":"2026-08-11T02:24:30.859449+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZBENNHMITN7CRGRYNXMSXVARP","json":"https://pith.science/pith/VZBENNHMITN7CRGRYNXMSXVARP.json","graph_json":"https://pith.science/api/pith-number/VZBENNHMITN7CRGRYNXMSXVARP/graph.json","events_json":"https://pith.science/api/pith-number/VZBENNHMITN7CRGRYNXMSXVARP/events.json","paper":"https://pith.science/paper/VZBENNHM"},"agent_actions":{"view_html":"https://pith.science/pith/VZBENNHMITN7CRGRYNXMSXVARP","download_json":"https://pith.science/pith/VZBENNHMITN7CRGRYNXMSXVARP.json","view_paper":"https://pith.science/paper/VZBENNHM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.09564&json=true","fetch_graph":"https://pith.science/api/pith-number/VZBENNHMITN7CRGRYNXMSXVARP/graph.json","fetch_events":"https://pith.science/api/pith-number/VZBENNHMITN7CRGRYNXMSXVARP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZBENNHMITN7CRGRYNXMSXVARP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZBENNHMITN7CRGRYNXMSXVARP/action/storage_attestation","attest_author":"https://pith.science/pith/VZBENNHMITN7CRGRYNXMSXVARP/action/author_attestation","sign_citation":"https://pith.science/pith/VZBENNHMITN7CRGRYNXMSXVARP/action/citation_signature","submit_replication":"https://pith.science/pith/VZBENNHMITN7CRGRYNXMSXVARP/action/replication_record"}},"created_at":"2026-08-11T02:24:30.859449+00:00","updated_at":"2026-08-11T02:24:30.859449+00:00"}