{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N73BUWF2IVRTFU3SDNTTYUSWBG","short_pith_number":"pith:N73BUWF2","schema_version":"1.0","canonical_sha256":"6ff61a58ba456332d3721b673c52560990996a8a5705392d38fce86020faa829","source":{"kind":"arxiv","id":"2607.15004","version":1},"attestation_state":"computed","paper":{"title":"CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Binbo Li, Da Zhang, Hanxuan Chen, Hanzhong Guo, Ji Pei, Kangli Wang, Ruilong Ren, Shuai Yuan, Songsheng Cheng, Tianle Zeng, Xiangyue Wang, Yunpeng Zhou","submitted_at":"2026-07-16T13:52:08Z","abstract_excerpt":"Dynamic target tracking is essential for Unmanned Aerial Vehicles (UAVs) operating in complex urban environments, where both the target and the camera viewpoint change continuously. Existing Vision-Language-Action (VLA) policies can track visible targets effectively, but their performance often degrades when buildings, vegetation, or roadside objects block the line of sight. During sustained occlusion, a policy may lose the target state, execute actions toward an incorrect region, and amplify this error through subsequent observations until re-acquisition becomes impossible. To this end, we pr"},"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":"2607.15004","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-16T13:52:08Z","cross_cats_sorted":[],"title_canon_sha256":"e6f5913c2aabb4e24a62a7878a13e3ed7cf85aa6d47d082cbb939bf658e3da2c","abstract_canon_sha256":"dbacb60a229b35c3aa6812a3322b19fdf7214e9ecab312548e539c10b6be5bbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:22:03.446903Z","signature_b64":"uHpte6+E9cGLFxTWN1sV4skurZkxwRxxEiHA9mFSxVgfePUCz7AXuHZuAoXJ3EUnLOlWtagmDffs3R7TKRpsBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ff61a58ba456332d3721b673c52560990996a8a5705392d38fce86020faa829","last_reissued_at":"2026-07-17T01:22:03.446055Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:22:03.446055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Binbo Li, Da Zhang, Hanxuan Chen, Hanzhong Guo, Ji Pei, Kangli Wang, Ruilong Ren, Shuai Yuan, Songsheng Cheng, Tianle Zeng, Xiangyue Wang, Yunpeng Zhou","submitted_at":"2026-07-16T13:52:08Z","abstract_excerpt":"Dynamic target tracking is essential for Unmanned Aerial Vehicles (UAVs) operating in complex urban environments, where both the target and the camera viewpoint change continuously. Existing Vision-Language-Action (VLA) policies can track visible targets effectively, but their performance often degrades when buildings, vegetation, or roadside objects block the line of sight. During sustained occlusion, a policy may lose the target state, execute actions toward an incorrect region, and amplify this error through subsequent observations until re-acquisition becomes impossible. To this end, we pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15004","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/2607.15004/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":"2607.15004","created_at":"2026-07-17T01:22:03.446486+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.15004v1","created_at":"2026-07-17T01:22:03.446486+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15004","created_at":"2026-07-17T01:22:03.446486+00:00"},{"alias_kind":"pith_short_12","alias_value":"N73BUWF2IVRT","created_at":"2026-07-17T01:22:03.446486+00:00"},{"alias_kind":"pith_short_16","alias_value":"N73BUWF2IVRTFU3S","created_at":"2026-07-17T01:22:03.446486+00:00"},{"alias_kind":"pith_short_8","alias_value":"N73BUWF2","created_at":"2026-07-17T01:22:03.446486+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/N73BUWF2IVRTFU3SDNTTYUSWBG","json":"https://pith.science/pith/N73BUWF2IVRTFU3SDNTTYUSWBG.json","graph_json":"https://pith.science/api/pith-number/N73BUWF2IVRTFU3SDNTTYUSWBG/graph.json","events_json":"https://pith.science/api/pith-number/N73BUWF2IVRTFU3SDNTTYUSWBG/events.json","paper":"https://pith.science/paper/N73BUWF2"},"agent_actions":{"view_html":"https://pith.science/pith/N73BUWF2IVRTFU3SDNTTYUSWBG","download_json":"https://pith.science/pith/N73BUWF2IVRTFU3SDNTTYUSWBG.json","view_paper":"https://pith.science/paper/N73BUWF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.15004&json=true","fetch_graph":"https://pith.science/api/pith-number/N73BUWF2IVRTFU3SDNTTYUSWBG/graph.json","fetch_events":"https://pith.science/api/pith-number/N73BUWF2IVRTFU3SDNTTYUSWBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N73BUWF2IVRTFU3SDNTTYUSWBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N73BUWF2IVRTFU3SDNTTYUSWBG/action/storage_attestation","attest_author":"https://pith.science/pith/N73BUWF2IVRTFU3SDNTTYUSWBG/action/author_attestation","sign_citation":"https://pith.science/pith/N73BUWF2IVRTFU3SDNTTYUSWBG/action/citation_signature","submit_replication":"https://pith.science/pith/N73BUWF2IVRTFU3SDNTTYUSWBG/action/replication_record"}},"created_at":"2026-07-17T01:22:03.446486+00:00","updated_at":"2026-07-17T01:22:03.446486+00:00"}