{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZXXXZJT57OJPA7RXEBHOG67PNW","short_pith_number":"pith:ZXXXZJT5","schema_version":"1.0","canonical_sha256":"cdef7ca67dfb92f07e37204ee37bef6d9e5c56f74696b12e67dc70279f218aa1","source":{"kind":"arxiv","id":"2607.10180","version":1},"attestation_state":"computed","paper":{"title":"ActiveFly-Bench: Aligning Embodied Question Answering with Vision-Language-Action for Aerial Embodied Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chen Gao, Haoyang Wang, Peizhi Tang, Shilong Ji, Shiquan Yu, Tianyi Lyu, Weichen Zhang, Xinlei Chen, Xin Zeng, Yinan Zhu, Yong Li, Zhiyuan Deng","submitted_at":"2026-07-11T07:58:04Z","abstract_excerpt":"We introduce ActiveFly-Bench, the first benchmark to bridge cyberspace reasoning and physical-world interaction for UAV embodied perception. The benchmark decomposes active perception into three hierarchical tasks: Aerial Embodied Question Answering (Air-EQA), Observation Behavior Planning (OBP), and Fine-grained Language-guided UAV Control (FLUC), explicitly connecting high-level task understanding, behavior planning, and low-level control. The datasets are collected from both real-world and simulated outdoor environments for training and evaluation. We further develop ActiveFly, a closed-loo"},"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":"2607.10180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-11T07:58:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"195e34dd2b8ad0da7efdb53686f9a8288d53306cf737ef840c4841ecb5a84cc7","abstract_canon_sha256":"c320bd605cc5d7805d52ba1095931d0b4d8f0d0911666d5643b752db916529e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:20:29.399394Z","signature_b64":"/c1suIGkgC/jPqYI4N0JTHIo+EIyfR5QkVUm4I1MvYAhbwwP3bAkLqvJsb+1/hZAdv5Ms2sDaVQPmIGkjfqrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdef7ca67dfb92f07e37204ee37bef6d9e5c56f74696b12e67dc70279f218aa1","last_reissued_at":"2026-07-14T01:20:29.398567Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:20:29.398567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ActiveFly-Bench: Aligning Embodied Question Answering with Vision-Language-Action for Aerial Embodied Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chen Gao, Haoyang Wang, Peizhi Tang, Shilong Ji, Shiquan Yu, Tianyi Lyu, Weichen Zhang, Xinlei Chen, Xin Zeng, Yinan Zhu, Yong Li, Zhiyuan Deng","submitted_at":"2026-07-11T07:58:04Z","abstract_excerpt":"We introduce ActiveFly-Bench, the first benchmark to bridge cyberspace reasoning and physical-world interaction for UAV embodied perception. The benchmark decomposes active perception into three hierarchical tasks: Aerial Embodied Question Answering (Air-EQA), Observation Behavior Planning (OBP), and Fine-grained Language-guided UAV Control (FLUC), explicitly connecting high-level task understanding, behavior planning, and low-level control. The datasets are collected from both real-world and simulated outdoor environments for training and evaluation. We further develop ActiveFly, a closed-loo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10180","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/2607.10180/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":"2607.10180","created_at":"2026-07-14T01:20:29.398984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10180v1","created_at":"2026-07-14T01:20:29.398984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10180","created_at":"2026-07-14T01:20:29.398984+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXXXZJT57OJP","created_at":"2026-07-14T01:20:29.398984+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXXXZJT57OJPA7RX","created_at":"2026-07-14T01:20:29.398984+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXXXZJT5","created_at":"2026-07-14T01:20:29.398984+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/ZXXXZJT57OJPA7RXEBHOG67PNW","json":"https://pith.science/pith/ZXXXZJT57OJPA7RXEBHOG67PNW.json","graph_json":"https://pith.science/api/pith-number/ZXXXZJT57OJPA7RXEBHOG67PNW/graph.json","events_json":"https://pith.science/api/pith-number/ZXXXZJT57OJPA7RXEBHOG67PNW/events.json","paper":"https://pith.science/paper/ZXXXZJT5"},"agent_actions":{"view_html":"https://pith.science/pith/ZXXXZJT57OJPA7RXEBHOG67PNW","download_json":"https://pith.science/pith/ZXXXZJT57OJPA7RXEBHOG67PNW.json","view_paper":"https://pith.science/paper/ZXXXZJT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10180&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXXXZJT57OJPA7RXEBHOG67PNW/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXXXZJT57OJPA7RXEBHOG67PNW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXXXZJT57OJPA7RXEBHOG67PNW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXXXZJT57OJPA7RXEBHOG67PNW/action/storage_attestation","attest_author":"https://pith.science/pith/ZXXXZJT57OJPA7RXEBHOG67PNW/action/author_attestation","sign_citation":"https://pith.science/pith/ZXXXZJT57OJPA7RXEBHOG67PNW/action/citation_signature","submit_replication":"https://pith.science/pith/ZXXXZJT57OJPA7RXEBHOG67PNW/action/replication_record"}},"created_at":"2026-07-14T01:20:29.398984+00:00","updated_at":"2026-07-14T01:20:29.398984+00:00"}