{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BFDB4ZL2XL2DR3WQORD7SPGA6B","short_pith_number":"pith:BFDB4ZL2","schema_version":"1.0","canonical_sha256":"09461e657abaf438eed07447f93cc0f046bb4ed127c919d775b1c4a02ae6ba93","source":{"kind":"arxiv","id":"2306.11300","version":5},"attestation_state":"computed","paper":{"title":"RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Jianwei Yin, Tiancheng Zhao, Yulong Guo, Zilun Zhang","submitted_at":"2023-06-20T05:30:59Z","abstract_excerpt":"Pre-trained Vision-Language Models (VLMs) utilizing extensive image-text paired data have demonstrated unprecedented image-text association capabilities, achieving remarkable results across various downstream tasks. A critical challenge is how to make use of existing large-scale pre-trained VLMs, which are trained on common objects, to perform the domain-specific transfer for accomplishing domain-related downstream tasks. A critical challenge is how to make use of existing large-scale pre-trained VLMs, which are trained on common objects, to perform the domain-specific transfer for accomplishi"},"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":"2306.11300","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-20T05:30:59Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"3621588ac4a26805d209a04b6a92c7b8b1ab495704b994d490e14d87d063d54b","abstract_canon_sha256":"1bb6dc003d26101ff85bca4392a1f84ebc58b45fac1abc6b33bf8848aa917a9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:28.437904Z","signature_b64":"9r+XeF25aafx2/QJqwYyIDKIOQC8TXhLjmveIp1ZS2ohfHoS//o4hnqbYkFIVn4nojoHxXVveSKHBGlpug6CDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09461e657abaf438eed07447f93cc0f046bb4ed127c919d775b1c4a02ae6ba93","last_reissued_at":"2026-07-05T09:04:28.437453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:28.437453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Jianwei Yin, Tiancheng Zhao, Yulong Guo, Zilun Zhang","submitted_at":"2023-06-20T05:30:59Z","abstract_excerpt":"Pre-trained Vision-Language Models (VLMs) utilizing extensive image-text paired data have demonstrated unprecedented image-text association capabilities, achieving remarkable results across various downstream tasks. A critical challenge is how to make use of existing large-scale pre-trained VLMs, which are trained on common objects, to perform the domain-specific transfer for accomplishing domain-related downstream tasks. A critical challenge is how to make use of existing large-scale pre-trained VLMs, which are trained on common objects, to perform the domain-specific transfer for accomplishi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11300","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/2306.11300/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":"2306.11300","created_at":"2026-07-05T09:04:28.437521+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.11300v5","created_at":"2026-07-05T09:04:28.437521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11300","created_at":"2026-07-05T09:04:28.437521+00:00"},{"alias_kind":"pith_short_12","alias_value":"BFDB4ZL2XL2D","created_at":"2026-07-05T09:04:28.437521+00:00"},{"alias_kind":"pith_short_16","alias_value":"BFDB4ZL2XL2DR3WQ","created_at":"2026-07-05T09:04:28.437521+00:00"},{"alias_kind":"pith_short_8","alias_value":"BFDB4ZL2","created_at":"2026-07-05T09:04:28.437521+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07758","citing_title":"Scalable and Trustworthy Earth Observation Foundation Models","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12542","citing_title":"Earth Science Foundation Models: From Perception to Reasoning and Discovery","ref_index":157,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12542","citing_title":"Earth Science Foundation Models: From Perception to Reasoning and Discovery","ref_index":157,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BFDB4ZL2XL2DR3WQORD7SPGA6B","json":"https://pith.science/pith/BFDB4ZL2XL2DR3WQORD7SPGA6B.json","graph_json":"https://pith.science/api/pith-number/BFDB4ZL2XL2DR3WQORD7SPGA6B/graph.json","events_json":"https://pith.science/api/pith-number/BFDB4ZL2XL2DR3WQORD7SPGA6B/events.json","paper":"https://pith.science/paper/BFDB4ZL2"},"agent_actions":{"view_html":"https://pith.science/pith/BFDB4ZL2XL2DR3WQORD7SPGA6B","download_json":"https://pith.science/pith/BFDB4ZL2XL2DR3WQORD7SPGA6B.json","view_paper":"https://pith.science/paper/BFDB4ZL2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.11300&json=true","fetch_graph":"https://pith.science/api/pith-number/BFDB4ZL2XL2DR3WQORD7SPGA6B/graph.json","fetch_events":"https://pith.science/api/pith-number/BFDB4ZL2XL2DR3WQORD7SPGA6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BFDB4ZL2XL2DR3WQORD7SPGA6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BFDB4ZL2XL2DR3WQORD7SPGA6B/action/storage_attestation","attest_author":"https://pith.science/pith/BFDB4ZL2XL2DR3WQORD7SPGA6B/action/author_attestation","sign_citation":"https://pith.science/pith/BFDB4ZL2XL2DR3WQORD7SPGA6B/action/citation_signature","submit_replication":"https://pith.science/pith/BFDB4ZL2XL2DR3WQORD7SPGA6B/action/replication_record"}},"created_at":"2026-07-05T09:04:28.437521+00:00","updated_at":"2026-07-05T09:04:28.437521+00:00"}