{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:27GK6HBV2GG7YDMCVAAJ6ZDP6D","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":"dd41f8cafef0dd2d29c8a4bc660185edccc3eefc6e42278ec218feeb84e18888","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-22T09:33:25Z","title_canon_sha256":"4319eea52ac2a7e21671636fc213b87b310efab62d25269cb4d8d183bce62571"},"schema_version":"1.0","source":{"id":"2408.12246","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12246","created_at":"2026-07-05T11:34:43Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12246v3","created_at":"2026-07-05T11:34:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12246","created_at":"2026-07-05T11:34:43Z"},{"alias_kind":"pith_short_12","alias_value":"27GK6HBV2GG7","created_at":"2026-07-05T11:34:43Z"},{"alias_kind":"pith_short_16","alias_value":"27GK6HBV2GG7YDMC","created_at":"2026-07-05T11:34:43Z"},{"alias_kind":"pith_short_8","alias_value":"27GK6HBV","created_at":"2026-07-05T11:34:43Z"}],"graph_snapshots":[{"event_id":"sha256:0452dc7ff98fe5697a1a87e95bd6ca3f391caa19aff0854d2f859ed4e40fa94f","target":"graph","created_at":"2026-07-05T11:34:43Z","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/2408.12246/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aerial object detection plays a crucial role in numerous applications. However, most existing methods focus on detecting predefined object categories, limiting their applicability in real-world open scenarios. In this paper, we extend aerial object detection to open scenarios through image-text collaboration and propose RT-OVAD, the first real-time open-vocabulary detector for aerial scenes. Specifically, we first introduce an image-to-text alignment loss to replace the conventional category regression loss, thereby eliminating category constraints. Next, we propose a lightweight image-text co","authors_text":"Chunxia Zhao, Guoting Wei, Haokui Zhang, Kelu Yao, Peng Wang, Rong Xiao, Xia Yuan, Xizhe Xue, Yu Liu, Zhenhao Shang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-22T09:33:25Z","title":"RT-OVAD: Real-Time Open-Vocabulary Aerial Object Detection via Image-Text Collaboration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12246","kind":"arxiv","version":3},"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:f5dfdb1e6ce8b5ee24ef68351ebe673da7530fc0cbdd7decd05f33e815704f5c","target":"record","created_at":"2026-07-05T11:34:43Z","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":"dd41f8cafef0dd2d29c8a4bc660185edccc3eefc6e42278ec218feeb84e18888","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-22T09:33:25Z","title_canon_sha256":"4319eea52ac2a7e21671636fc213b87b310efab62d25269cb4d8d183bce62571"},"schema_version":"1.0","source":{"id":"2408.12246","kind":"arxiv","version":3}},"canonical_sha256":"d7ccaf1c35d18dfc0d82a8009f646ff0d44017d28ded3658c00997097f932632","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7ccaf1c35d18dfc0d82a8009f646ff0d44017d28ded3658c00997097f932632","first_computed_at":"2026-07-05T11:34:43.101099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:43.101099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z8wUHkO5ptrDSGbnhEMEu453fCUn5WLJ50fXVihmiazoA1mc9VYkoa74OFoIs0XXbE1RSue0DV7P6MNl8RHuCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:43.101546Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.12246","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5dfdb1e6ce8b5ee24ef68351ebe673da7530fc0cbdd7decd05f33e815704f5c","sha256:0452dc7ff98fe5697a1a87e95bd6ca3f391caa19aff0854d2f859ed4e40fa94f"],"state_sha256":"b941440deab28675046a482d5c4c06245882ecd6ae4ad460dadb0b8e6ba57742"}