{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NMVGROBD62QDP6DXI3EJ4PD7CU","short_pith_number":"pith:NMVGROBD","schema_version":"1.0","canonical_sha256":"6b2a68b823f6a037f87746c89e3c7f153af7ef90f7f7351c24a1241a6332363b","source":{"kind":"arxiv","id":"2307.15266","version":1},"attestation_state":"computed","paper":{"title":"RSGPT: A Remote Sensing Vision Language Model and Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Congcong Wen, Jianlong Yuan, Xiang Li, Xiaonan Lu, Yuan Hu","submitted_at":"2023-07-28T02:23:35Z","abstract_excerpt":"The emergence of large-scale large language models, with GPT-4 as a prominent example, has significantly propelled the rapid advancement of artificial general intelligence and sparked the revolution of Artificial Intelligence 2.0. In the realm of remote sensing (RS), there is a growing interest in developing large vision language models (VLMs) specifically tailored for data analysis in this domain. However, current research predominantly revolves around visual recognition tasks, lacking comprehensive, large-scale image-text datasets that are aligned and suitable for training large VLMs, which "},"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":"2307.15266","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-28T02:23:35Z","cross_cats_sorted":[],"title_canon_sha256":"d31fe3c549a641cd3a4a63dbf68a8f608892301822f3d09ff6ee1d52ac11b9aa","abstract_canon_sha256":"2cadf2f5562e4387d2b9a540df458009c987c10bbb297d492dd5696f2b2bc0f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:32.760154Z","signature_b64":"LZOMViSHOCBnNyJiQbJJnW8NDHTeGzvFZ/SX2zaiJ94eGcBJ3yhmRmkyn+mywoo6W1RD9oSzUN/E/Zhio5ugAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b2a68b823f6a037f87746c89e3c7f153af7ef90f7f7351c24a1241a6332363b","last_reissued_at":"2026-07-05T06:35:32.759760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:32.759760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RSGPT: A Remote Sensing Vision Language Model and Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Congcong Wen, Jianlong Yuan, Xiang Li, Xiaonan Lu, Yuan Hu","submitted_at":"2023-07-28T02:23:35Z","abstract_excerpt":"The emergence of large-scale large language models, with GPT-4 as a prominent example, has significantly propelled the rapid advancement of artificial general intelligence and sparked the revolution of Artificial Intelligence 2.0. In the realm of remote sensing (RS), there is a growing interest in developing large vision language models (VLMs) specifically tailored for data analysis in this domain. However, current research predominantly revolves around visual recognition tasks, lacking comprehensive, large-scale image-text datasets that are aligned and suitable for training large VLMs, which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15266","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/2307.15266/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":"2307.15266","created_at":"2026-07-05T06:35:32.759817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.15266v1","created_at":"2026-07-05T06:35:32.759817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15266","created_at":"2026-07-05T06:35:32.759817+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMVGROBD62QD","created_at":"2026-07-05T06:35:32.759817+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMVGROBD62QDP6DX","created_at":"2026-07-05T06:35:32.759817+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMVGROBD","created_at":"2026-07-05T06:35:32.759817+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28266","citing_title":"RSICCLLM: A Multimodal Large Language Model for Remote Sensing Image Change Captioning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30168","citing_title":"OmniCD: A Foundational Framework for Remote Sensing Image Change Detection Guided by Multimodal Semantics","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13305","citing_title":"WildfireVLM: AI-powered Analysis for Early Wildfire Detection and Risk Assessment Using Satellite Imagery","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14475","citing_title":"GeoVista: Visually Grounded Active Perception for Ultra-High-Resolution Remote Sensing Understanding","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22333","citing_title":"ChangeQuery: Advancing Remote Sensing Change Analysis for Natural and Human-Induced Disasters from Visual Detection to Semantic Understanding","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07562","citing_title":"Beyond GSD-as-Token: Continuous Scale Conditioning for Remote Sensing VLMs","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14707","citing_title":"Geo2Sound: A Scalable Geo-Aligned Framework for Soundscape Generation from Satellite Imagery","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NMVGROBD62QDP6DXI3EJ4PD7CU","json":"https://pith.science/pith/NMVGROBD62QDP6DXI3EJ4PD7CU.json","graph_json":"https://pith.science/api/pith-number/NMVGROBD62QDP6DXI3EJ4PD7CU/graph.json","events_json":"https://pith.science/api/pith-number/NMVGROBD62QDP6DXI3EJ4PD7CU/events.json","paper":"https://pith.science/paper/NMVGROBD"},"agent_actions":{"view_html":"https://pith.science/pith/NMVGROBD62QDP6DXI3EJ4PD7CU","download_json":"https://pith.science/pith/NMVGROBD62QDP6DXI3EJ4PD7CU.json","view_paper":"https://pith.science/paper/NMVGROBD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.15266&json=true","fetch_graph":"https://pith.science/api/pith-number/NMVGROBD62QDP6DXI3EJ4PD7CU/graph.json","fetch_events":"https://pith.science/api/pith-number/NMVGROBD62QDP6DXI3EJ4PD7CU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMVGROBD62QDP6DXI3EJ4PD7CU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMVGROBD62QDP6DXI3EJ4PD7CU/action/storage_attestation","attest_author":"https://pith.science/pith/NMVGROBD62QDP6DXI3EJ4PD7CU/action/author_attestation","sign_citation":"https://pith.science/pith/NMVGROBD62QDP6DXI3EJ4PD7CU/action/citation_signature","submit_replication":"https://pith.science/pith/NMVGROBD62QDP6DXI3EJ4PD7CU/action/replication_record"}},"created_at":"2026-07-05T06:35:32.759817+00:00","updated_at":"2026-07-05T06:35:32.759817+00:00"}