{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZUJVQMDLL6GCVPKS4MDEWBARWB","short_pith_number":"pith:ZUJVQMDL","schema_version":"1.0","canonical_sha256":"cd1358306b5f8c2abd52e3064b0411b05922f1a6f439bed2927bde06a3591e9c","source":{"kind":"arxiv","id":"2509.06011","version":2},"attestation_state":"computed","paper":{"title":"Light-Weight Cross-Modal Enhancement Method with Benchmark Construction for UAV-based Open-Vocabulary Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Wu, Dong Zhou, Jianfeng Lv, Weijie He, Xinjie Li, Zhenhai Weng, Zhongliang Yu","submitted_at":"2025-09-07T10:59:02Z","abstract_excerpt":"Open-Vocabulary Object Detection (OVD) faces severe performance degradation when applied to UAV imagery due to the domain gap from ground-level datasets. To address this challenge, we propose a complete UAV-oriented solution that combines both dataset construction and model innovation. First, we design a refined UAV-Label Engine, which efficiently resolves annotation redundancy, inconsistency, and ambiguity, enabling the generation of largescale UAV datasets. Based on this engine, we construct two new benchmarks: UAVDE-2M, with over 2.4M instances across 1,800+ categories, and UAVCAP-15K, prov"},"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":"2509.06011","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-07T10:59:02Z","cross_cats_sorted":[],"title_canon_sha256":"2d2af502f47617d6e827307807543f3956b0df089c3c651280ef4c7e0178a83d","abstract_canon_sha256":"acfb2f7055a41ca637eb209df782b1eac31918824b57c07789b5b39122c16b3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:12.264008Z","signature_b64":"9DOr2dB6/hyQWiAtrIyH/kuVha7tnriGBJZTYfMLjdjksATdG0u7nPiJ8eumLvHMiCeZyVArkh2luvTxcTZTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd1358306b5f8c2abd52e3064b0411b05922f1a6f439bed2927bde06a3591e9c","last_reissued_at":"2026-07-05T12:07:12.263550Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:12.263550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Light-Weight Cross-Modal Enhancement Method with Benchmark Construction for UAV-based Open-Vocabulary Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Wu, Dong Zhou, Jianfeng Lv, Weijie He, Xinjie Li, Zhenhai Weng, Zhongliang Yu","submitted_at":"2025-09-07T10:59:02Z","abstract_excerpt":"Open-Vocabulary Object Detection (OVD) faces severe performance degradation when applied to UAV imagery due to the domain gap from ground-level datasets. To address this challenge, we propose a complete UAV-oriented solution that combines both dataset construction and model innovation. First, we design a refined UAV-Label Engine, which efficiently resolves annotation redundancy, inconsistency, and ambiguity, enabling the generation of largescale UAV datasets. Based on this engine, we construct two new benchmarks: UAVDE-2M, with over 2.4M instances across 1,800+ categories, and UAVCAP-15K, prov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06011","kind":"arxiv","version":2},"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/2509.06011/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":"2509.06011","created_at":"2026-07-05T12:07:12.263606+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06011v2","created_at":"2026-07-05T12:07:12.263606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06011","created_at":"2026-07-05T12:07:12.263606+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZUJVQMDLL6GC","created_at":"2026-07-05T12:07:12.263606+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZUJVQMDLL6GCVPKS","created_at":"2026-07-05T12:07:12.263606+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZUJVQMDL","created_at":"2026-07-05T12:07:12.263606+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/ZUJVQMDLL6GCVPKS4MDEWBARWB","json":"https://pith.science/pith/ZUJVQMDLL6GCVPKS4MDEWBARWB.json","graph_json":"https://pith.science/api/pith-number/ZUJVQMDLL6GCVPKS4MDEWBARWB/graph.json","events_json":"https://pith.science/api/pith-number/ZUJVQMDLL6GCVPKS4MDEWBARWB/events.json","paper":"https://pith.science/paper/ZUJVQMDL"},"agent_actions":{"view_html":"https://pith.science/pith/ZUJVQMDLL6GCVPKS4MDEWBARWB","download_json":"https://pith.science/pith/ZUJVQMDLL6GCVPKS4MDEWBARWB.json","view_paper":"https://pith.science/paper/ZUJVQMDL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06011&json=true","fetch_graph":"https://pith.science/api/pith-number/ZUJVQMDLL6GCVPKS4MDEWBARWB/graph.json","fetch_events":"https://pith.science/api/pith-number/ZUJVQMDLL6GCVPKS4MDEWBARWB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZUJVQMDLL6GCVPKS4MDEWBARWB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZUJVQMDLL6GCVPKS4MDEWBARWB/action/storage_attestation","attest_author":"https://pith.science/pith/ZUJVQMDLL6GCVPKS4MDEWBARWB/action/author_attestation","sign_citation":"https://pith.science/pith/ZUJVQMDLL6GCVPKS4MDEWBARWB/action/citation_signature","submit_replication":"https://pith.science/pith/ZUJVQMDLL6GCVPKS4MDEWBARWB/action/replication_record"}},"created_at":"2026-07-05T12:07:12.263606+00:00","updated_at":"2026-07-05T12:07:12.263606+00:00"}