{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HUOW2B57OCIZBGRLHBDVJ5MUNT","short_pith_number":"pith:HUOW2B57","schema_version":"1.0","canonical_sha256":"3d1d6d07bf7091909a2b384754f5946ce0b0c3b9a7317f9c4f697f0573bbfbc1","source":{"kind":"arxiv","id":"2311.12751","version":4},"attestation_state":"computed","paper":{"title":"Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Meng Chu, Tat-Seng Chua, Tingyu Wang, Wei Ji, Zhedong Zheng","submitted_at":"2023-11-21T17:52:30Z","abstract_excerpt":"Navigating drones through natural language commands remains challenging due to the dearth of accessible multi-modal datasets and the stringent precision requirements for aligning visual and textual data. To address this pressing need, we introduce GeoText-1652, a new natural language-guided geo-localization benchmark. This dataset is systematically constructed through an interactive human-computer process leveraging Large Language Model (LLM) driven annotation techniques in conjunction with pre-trained vision models. GeoText-1652 extends the established University-1652 image dataset with spati"},"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":"2311.12751","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-21T17:52:30Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"df72caacb3617a5b96de0c6bda459a1bae92288e7c5a871f889cb6837ed14f7a","abstract_canon_sha256":"10796c7eafff43b37b8b5ea25f91c39fd74bdb27bef748c961aaabc8358be73f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:25.752214Z","signature_b64":"GEJBSZjjT0PZ0RGesWxg7aOi/LOP7bgejxEzEN1AgE+LMmBeHFzfWRtyd231EL8aoH9Lmvqf3GnPU8Vl0kcsBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d1d6d07bf7091909a2b384754f5946ce0b0c3b9a7317f9c4f697f0573bbfbc1","last_reissued_at":"2026-07-05T08:50:25.751812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:25.751812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Meng Chu, Tat-Seng Chua, Tingyu Wang, Wei Ji, Zhedong Zheng","submitted_at":"2023-11-21T17:52:30Z","abstract_excerpt":"Navigating drones through natural language commands remains challenging due to the dearth of accessible multi-modal datasets and the stringent precision requirements for aligning visual and textual data. To address this pressing need, we introduce GeoText-1652, a new natural language-guided geo-localization benchmark. This dataset is systematically constructed through an interactive human-computer process leveraging Large Language Model (LLM) driven annotation techniques in conjunction with pre-trained vision models. GeoText-1652 extends the established University-1652 image dataset with spati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12751","kind":"arxiv","version":4},"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/2311.12751/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":"2311.12751","created_at":"2026-07-05T08:50:25.751876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.12751v4","created_at":"2026-07-05T08:50:25.751876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12751","created_at":"2026-07-05T08:50:25.751876+00:00"},{"alias_kind":"pith_short_12","alias_value":"HUOW2B57OCIZ","created_at":"2026-07-05T08:50:25.751876+00:00"},{"alias_kind":"pith_short_16","alias_value":"HUOW2B57OCIZBGRL","created_at":"2026-07-05T08:50:25.751876+00:00"},{"alias_kind":"pith_short_8","alias_value":"HUOW2B57","created_at":"2026-07-05T08:50:25.751876+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.17007","citing_title":"Where am I? Cross-View Geo-localization with Natural Language Descriptions","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HUOW2B57OCIZBGRLHBDVJ5MUNT","json":"https://pith.science/pith/HUOW2B57OCIZBGRLHBDVJ5MUNT.json","graph_json":"https://pith.science/api/pith-number/HUOW2B57OCIZBGRLHBDVJ5MUNT/graph.json","events_json":"https://pith.science/api/pith-number/HUOW2B57OCIZBGRLHBDVJ5MUNT/events.json","paper":"https://pith.science/paper/HUOW2B57"},"agent_actions":{"view_html":"https://pith.science/pith/HUOW2B57OCIZBGRLHBDVJ5MUNT","download_json":"https://pith.science/pith/HUOW2B57OCIZBGRLHBDVJ5MUNT.json","view_paper":"https://pith.science/paper/HUOW2B57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.12751&json=true","fetch_graph":"https://pith.science/api/pith-number/HUOW2B57OCIZBGRLHBDVJ5MUNT/graph.json","fetch_events":"https://pith.science/api/pith-number/HUOW2B57OCIZBGRLHBDVJ5MUNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HUOW2B57OCIZBGRLHBDVJ5MUNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HUOW2B57OCIZBGRLHBDVJ5MUNT/action/storage_attestation","attest_author":"https://pith.science/pith/HUOW2B57OCIZBGRLHBDVJ5MUNT/action/author_attestation","sign_citation":"https://pith.science/pith/HUOW2B57OCIZBGRLHBDVJ5MUNT/action/citation_signature","submit_replication":"https://pith.science/pith/HUOW2B57OCIZBGRLHBDVJ5MUNT/action/replication_record"}},"created_at":"2026-07-05T08:50:25.751876+00:00","updated_at":"2026-07-05T08:50:25.751876+00:00"}