{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JIG57MFVDYSQ3XMELEO7X2DSIW","short_pith_number":"pith:JIG57MFV","schema_version":"1.0","canonical_sha256":"4a0ddfb0b51e250ddd84591dfbe87245beae966b8475883afc3320fbacd84e46","source":{"kind":"arxiv","id":"2312.12222","version":1},"attestation_state":"computed","paper":{"title":"EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailong Ma, Junjue Wang, Yanfei Zhong, Zhuo Zheng, Zihang Chen","submitted_at":"2023-12-19T15:11:32Z","abstract_excerpt":"Earth vision research typically focuses on extracting geospatial object locations and categories but neglects the exploration of relations between objects and comprehensive reasoning. Based on city planning needs, we develop a multi-modal multi-task VQA dataset (EarthVQA) to advance relational reasoning-based judging, counting, and comprehensive analysis. The EarthVQA dataset contains 6000 images, corresponding semantic masks, and 208,593 QA pairs with urban and rural governance requirements embedded. As objects are the basis for complex relational reasoning, we propose a Semantic OBject Aware"},"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":"2312.12222","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T15:11:32Z","cross_cats_sorted":[],"title_canon_sha256":"df61dd2a5b44de321d4f153963e6a1b242dd4554e06653b4fd740df863f1fd7b","abstract_canon_sha256":"a251b98a2a9fce4819d848fafaf9e2aa21f56f125911540d91ca1b3e68d66ad4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:00.612449Z","signature_b64":"/As/5deIcFaOYxrWnF9BOLAZuaeaEUd9Tkmw9vwMjCl4khDurDei776xuV6OejQhxgByI9LDblGrmS9oWKdzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a0ddfb0b51e250ddd84591dfbe87245beae966b8475883afc3320fbacd84e46","last_reissued_at":"2026-07-05T07:26:00.611920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:00.611920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailong Ma, Junjue Wang, Yanfei Zhong, Zhuo Zheng, Zihang Chen","submitted_at":"2023-12-19T15:11:32Z","abstract_excerpt":"Earth vision research typically focuses on extracting geospatial object locations and categories but neglects the exploration of relations between objects and comprehensive reasoning. Based on city planning needs, we develop a multi-modal multi-task VQA dataset (EarthVQA) to advance relational reasoning-based judging, counting, and comprehensive analysis. The EarthVQA dataset contains 6000 images, corresponding semantic masks, and 208,593 QA pairs with urban and rural governance requirements embedded. As objects are the basis for complex relational reasoning, we propose a Semantic OBject Aware"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12222","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/2312.12222/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":"2312.12222","created_at":"2026-07-05T07:26:00.611980+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.12222v1","created_at":"2026-07-05T07:26:00.611980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12222","created_at":"2026-07-05T07:26:00.611980+00:00"},{"alias_kind":"pith_short_12","alias_value":"JIG57MFVDYSQ","created_at":"2026-07-05T07:26:00.611980+00:00"},{"alias_kind":"pith_short_16","alias_value":"JIG57MFVDYSQ3XME","created_at":"2026-07-05T07:26:00.611980+00:00"},{"alias_kind":"pith_short_8","alias_value":"JIG57MFV","created_at":"2026-07-05T07:26:00.611980+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.05377","citing_title":"Can Vision-Language Models Think from the Sky? Unifying UAV Reasoning and Generation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04409","citing_title":"UAV as Urban Construction Change Monitor: A New Benchmark and Change Captioning Model","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JIG57MFVDYSQ3XMELEO7X2DSIW","json":"https://pith.science/pith/JIG57MFVDYSQ3XMELEO7X2DSIW.json","graph_json":"https://pith.science/api/pith-number/JIG57MFVDYSQ3XMELEO7X2DSIW/graph.json","events_json":"https://pith.science/api/pith-number/JIG57MFVDYSQ3XMELEO7X2DSIW/events.json","paper":"https://pith.science/paper/JIG57MFV"},"agent_actions":{"view_html":"https://pith.science/pith/JIG57MFVDYSQ3XMELEO7X2DSIW","download_json":"https://pith.science/pith/JIG57MFVDYSQ3XMELEO7X2DSIW.json","view_paper":"https://pith.science/paper/JIG57MFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.12222&json=true","fetch_graph":"https://pith.science/api/pith-number/JIG57MFVDYSQ3XMELEO7X2DSIW/graph.json","fetch_events":"https://pith.science/api/pith-number/JIG57MFVDYSQ3XMELEO7X2DSIW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JIG57MFVDYSQ3XMELEO7X2DSIW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JIG57MFVDYSQ3XMELEO7X2DSIW/action/storage_attestation","attest_author":"https://pith.science/pith/JIG57MFVDYSQ3XMELEO7X2DSIW/action/author_attestation","sign_citation":"https://pith.science/pith/JIG57MFVDYSQ3XMELEO7X2DSIW/action/citation_signature","submit_replication":"https://pith.science/pith/JIG57MFVDYSQ3XMELEO7X2DSIW/action/replication_record"}},"created_at":"2026-07-05T07:26:00.611980+00:00","updated_at":"2026-07-05T07:26:00.611980+00:00"}