{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:E2QC5DIFLHV3PXC4BKKBUSNIZI","short_pith_number":"pith:E2QC5DIF","schema_version":"1.0","canonical_sha256":"26a02e8d0559ebb7dc5c0a941a49a8ca225172d0b3d04ee512cbc3f9ac1991ea","source":{"kind":"arxiv","id":"2308.11561","version":5},"attestation_state":"computed","paper":{"title":"Target-Grounded Graph-Aware Transformer for Aerial Vision-and-Dialog Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong An, Kehan Chen, Yan Huang, Yifei Su, Yuan Xu","submitted_at":"2023-08-22T16:45:35Z","abstract_excerpt":"This report details the methods of the winning entry of the AVDN Challenge in ICCV CLVL 2023. The competition addresses the Aerial Navigation from Dialog History (ANDH) task, which requires a drone agent to associate dialog history with aerial observations to reach the destination. For better cross-modal grounding abilities of the drone agent, we propose a Target-Grounded Graph-Aware Transformer (TG-GAT) framework. Concretely, TG-GAT first leverages a graph-aware transformer to capture spatiotemporal dependency, which benefits navigation state tracking and robust action planning. In addition,a"},"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":"2308.11561","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-22T16:45:35Z","cross_cats_sorted":[],"title_canon_sha256":"c4a24b28312710b41fc1bd3581fc1b4a0920d6ba024e11f5e9f61d5d4292964b","abstract_canon_sha256":"8c592250ad9f00dc168f322ac97e30b616c47ba77dab3467a0fc1a178a0a2486"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:59.799446Z","signature_b64":"gvJAFdRhXEY081XXosTIR3NK/KoRG9RHTMG0lignyfVpoFra5MUz4SHt/nSVb1z7PO2t/VN/u5Krhv4FlxuICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26a02e8d0559ebb7dc5c0a941a49a8ca225172d0b3d04ee512cbc3f9ac1991ea","last_reissued_at":"2026-07-05T07:23:59.799007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:59.799007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Target-Grounded Graph-Aware Transformer for Aerial Vision-and-Dialog Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong An, Kehan Chen, Yan Huang, Yifei Su, Yuan Xu","submitted_at":"2023-08-22T16:45:35Z","abstract_excerpt":"This report details the methods of the winning entry of the AVDN Challenge in ICCV CLVL 2023. The competition addresses the Aerial Navigation from Dialog History (ANDH) task, which requires a drone agent to associate dialog history with aerial observations to reach the destination. For better cross-modal grounding abilities of the drone agent, we propose a Target-Grounded Graph-Aware Transformer (TG-GAT) framework. Concretely, TG-GAT first leverages a graph-aware transformer to capture spatiotemporal dependency, which benefits navigation state tracking and robust action planning. In addition,a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11561","kind":"arxiv","version":5},"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/2308.11561/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":"2308.11561","created_at":"2026-07-05T07:23:59.799069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.11561v5","created_at":"2026-07-05T07:23:59.799069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11561","created_at":"2026-07-05T07:23:59.799069+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2QC5DIFLHV3","created_at":"2026-07-05T07:23:59.799069+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2QC5DIFLHV3PXC4","created_at":"2026-07-05T07:23:59.799069+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2QC5DIF","created_at":"2026-07-05T07:23:59.799069+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07705","citing_title":"Vision-Language Navigation for Aerial Robots: Towards the Era of Large Language Models","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13654","citing_title":"Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap","ref_index":78,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E2QC5DIFLHV3PXC4BKKBUSNIZI","json":"https://pith.science/pith/E2QC5DIFLHV3PXC4BKKBUSNIZI.json","graph_json":"https://pith.science/api/pith-number/E2QC5DIFLHV3PXC4BKKBUSNIZI/graph.json","events_json":"https://pith.science/api/pith-number/E2QC5DIFLHV3PXC4BKKBUSNIZI/events.json","paper":"https://pith.science/paper/E2QC5DIF"},"agent_actions":{"view_html":"https://pith.science/pith/E2QC5DIFLHV3PXC4BKKBUSNIZI","download_json":"https://pith.science/pith/E2QC5DIFLHV3PXC4BKKBUSNIZI.json","view_paper":"https://pith.science/paper/E2QC5DIF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.11561&json=true","fetch_graph":"https://pith.science/api/pith-number/E2QC5DIFLHV3PXC4BKKBUSNIZI/graph.json","fetch_events":"https://pith.science/api/pith-number/E2QC5DIFLHV3PXC4BKKBUSNIZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2QC5DIFLHV3PXC4BKKBUSNIZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2QC5DIFLHV3PXC4BKKBUSNIZI/action/storage_attestation","attest_author":"https://pith.science/pith/E2QC5DIFLHV3PXC4BKKBUSNIZI/action/author_attestation","sign_citation":"https://pith.science/pith/E2QC5DIFLHV3PXC4BKKBUSNIZI/action/citation_signature","submit_replication":"https://pith.science/pith/E2QC5DIFLHV3PXC4BKKBUSNIZI/action/replication_record"}},"created_at":"2026-07-05T07:23:59.799069+00:00","updated_at":"2026-07-05T07:23:59.799069+00:00"}