{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U7EKVKUTKREOT52JCWXHIXFH7P","short_pith_number":"pith:U7EKVKUT","schema_version":"1.0","canonical_sha256":"a7c8aaaa935448e9f74915ae745ca7fbe970181d8a378c81813e94404b027371","source":{"kind":"arxiv","id":"2403.20213","version":4},"attestation_state":"computed","paper":{"title":"VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Pang, Conghui He, Gui-Song Xia, Jiang Wu, Jiaxing Sun, Jiayu Li, Litong Feng, Shuai Wang, Weijia Li, Xingxing Weng, Yi Liu","submitted_at":"2024-03-29T14:50:43Z","abstract_excerpt":"This paper develops a Versatile and Honest vision language Model (VHM) for remote sensing image analysis. VHM is built on a large-scale remote sensing image-text dataset with rich-content captions (VersaD), and an honest instruction dataset comprising both factual and deceptive questions (HnstD). Unlike prevailing remote sensing image-text datasets, in which image captions focus on a few prominent objects and their relationships, VersaD captions provide detailed information about image properties, object attributes, and the overall scene. This comprehensive captioning enables VHM to thoroughly"},"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":"2403.20213","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-29T14:50:43Z","cross_cats_sorted":[],"title_canon_sha256":"ed2227600ce38dca5f6521f3c5034eb3f016a639e54baf2d108973963d76fb1e","abstract_canon_sha256":"fc185cd4e5870e00314d7350b8792816bcc4d458731412b8e7aedb7518f23170"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:31.772852Z","signature_b64":"+w5zQZThultEHvFR3WAtIG+yfCBz4XGerbiPuVzbmozWPt6KoMHv4U4Vw5ViM56iH6GpYmR36ETZKj6dR9OnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7c8aaaa935448e9f74915ae745ca7fbe970181d8a378c81813e94404b027371","last_reissued_at":"2026-07-05T09:51:31.772296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:31.772296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Pang, Conghui He, Gui-Song Xia, Jiang Wu, Jiaxing Sun, Jiayu Li, Litong Feng, Shuai Wang, Weijia Li, Xingxing Weng, Yi Liu","submitted_at":"2024-03-29T14:50:43Z","abstract_excerpt":"This paper develops a Versatile and Honest vision language Model (VHM) for remote sensing image analysis. VHM is built on a large-scale remote sensing image-text dataset with rich-content captions (VersaD), and an honest instruction dataset comprising both factual and deceptive questions (HnstD). Unlike prevailing remote sensing image-text datasets, in which image captions focus on a few prominent objects and their relationships, VersaD captions provide detailed information about image properties, object attributes, and the overall scene. This comprehensive captioning enables VHM to thoroughly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.20213","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/2403.20213/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":"2403.20213","created_at":"2026-07-05T09:51:31.772367+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.20213v4","created_at":"2026-07-05T09:51:31.772367+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.20213","created_at":"2026-07-05T09:51:31.772367+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7EKVKUTKREO","created_at":"2026-07-05T09:51:31.772367+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7EKVKUTKREOT52J","created_at":"2026-07-05T09:51:31.772367+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7EKVKUT","created_at":"2026-07-05T09:51:31.772367+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01050","citing_title":"GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervision","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11122","citing_title":"Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U7EKVKUTKREOT52JCWXHIXFH7P","json":"https://pith.science/pith/U7EKVKUTKREOT52JCWXHIXFH7P.json","graph_json":"https://pith.science/api/pith-number/U7EKVKUTKREOT52JCWXHIXFH7P/graph.json","events_json":"https://pith.science/api/pith-number/U7EKVKUTKREOT52JCWXHIXFH7P/events.json","paper":"https://pith.science/paper/U7EKVKUT"},"agent_actions":{"view_html":"https://pith.science/pith/U7EKVKUTKREOT52JCWXHIXFH7P","download_json":"https://pith.science/pith/U7EKVKUTKREOT52JCWXHIXFH7P.json","view_paper":"https://pith.science/paper/U7EKVKUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.20213&json=true","fetch_graph":"https://pith.science/api/pith-number/U7EKVKUTKREOT52JCWXHIXFH7P/graph.json","fetch_events":"https://pith.science/api/pith-number/U7EKVKUTKREOT52JCWXHIXFH7P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7EKVKUTKREOT52JCWXHIXFH7P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7EKVKUTKREOT52JCWXHIXFH7P/action/storage_attestation","attest_author":"https://pith.science/pith/U7EKVKUTKREOT52JCWXHIXFH7P/action/author_attestation","sign_citation":"https://pith.science/pith/U7EKVKUTKREOT52JCWXHIXFH7P/action/citation_signature","submit_replication":"https://pith.science/pith/U7EKVKUTKREOT52JCWXHIXFH7P/action/replication_record"}},"created_at":"2026-07-05T09:51:31.772367+00:00","updated_at":"2026-07-05T09:51:31.772367+00:00"}