{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M34OYQLSVPBEOKHDBAPD6DGVM7","short_pith_number":"pith:M34OYQLS","schema_version":"1.0","canonical_sha256":"66f8ec4172abc24728e3081e3f0cd567d69b2cc399e999bf8422a48fd2c706db","source":{"kind":"arxiv","id":"2409.07048","version":1},"attestation_state":"computed","paper":{"title":"Pushing the Limits of Vision-Language Models in Remote Sensing without Human Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donggeun Yu, Junghoon Seo, Keumgang Cha","submitted_at":"2024-09-11T06:36:08Z","abstract_excerpt":"The prominence of generalized foundation models in vision-language integration has witnessed a surge, given their multifarious applications. Within the natural domain, the procurement of vision-language datasets to construct these foundation models is facilitated by their abundant availability and the ease of web crawling. Conversely, in the remote sensing domain, although vision-language datasets exist, their volume is suboptimal for constructing robust foundation models. This study introduces an approach to curate vision-language datasets by employing an image decoding machine learning model"},"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":"2409.07048","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-11T06:36:08Z","cross_cats_sorted":[],"title_canon_sha256":"52516e7fb4bed62bfac2a1e5824691d1b6204d4c777ccb686d59694c0a81de9f","abstract_canon_sha256":"0b4a40d2df5cc839ab24ea542f65a4538432c3c295bed98cff23a6624317dbd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:44.856377Z","signature_b64":"GdDOmrYQkOMZoJ2/OtXVpPw7Q1xpW7A6Lh/OTAJ7/6GY93RgonwLbaXefUQngIg0E5QtXGQGrdSYEnN8bUJIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66f8ec4172abc24728e3081e3f0cd567d69b2cc399e999bf8422a48fd2c706db","last_reissued_at":"2026-07-05T09:05:44.855934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:44.855934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pushing the Limits of Vision-Language Models in Remote Sensing without Human Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donggeun Yu, Junghoon Seo, Keumgang Cha","submitted_at":"2024-09-11T06:36:08Z","abstract_excerpt":"The prominence of generalized foundation models in vision-language integration has witnessed a surge, given their multifarious applications. Within the natural domain, the procurement of vision-language datasets to construct these foundation models is facilitated by their abundant availability and the ease of web crawling. Conversely, in the remote sensing domain, although vision-language datasets exist, their volume is suboptimal for constructing robust foundation models. This study introduces an approach to curate vision-language datasets by employing an image decoding machine learning model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07048","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/2409.07048/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":"2409.07048","created_at":"2026-07-05T09:05:44.855991+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.07048v1","created_at":"2026-07-05T09:05:44.855991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07048","created_at":"2026-07-05T09:05:44.855991+00:00"},{"alias_kind":"pith_short_12","alias_value":"M34OYQLSVPBE","created_at":"2026-07-05T09:05:44.855991+00:00"},{"alias_kind":"pith_short_16","alias_value":"M34OYQLSVPBEOKHD","created_at":"2026-07-05T09:05:44.855991+00:00"},{"alias_kind":"pith_short_8","alias_value":"M34OYQLS","created_at":"2026-07-05T09:05:44.855991+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16756","citing_title":"Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M34OYQLSVPBEOKHDBAPD6DGVM7","json":"https://pith.science/pith/M34OYQLSVPBEOKHDBAPD6DGVM7.json","graph_json":"https://pith.science/api/pith-number/M34OYQLSVPBEOKHDBAPD6DGVM7/graph.json","events_json":"https://pith.science/api/pith-number/M34OYQLSVPBEOKHDBAPD6DGVM7/events.json","paper":"https://pith.science/paper/M34OYQLS"},"agent_actions":{"view_html":"https://pith.science/pith/M34OYQLSVPBEOKHDBAPD6DGVM7","download_json":"https://pith.science/pith/M34OYQLSVPBEOKHDBAPD6DGVM7.json","view_paper":"https://pith.science/paper/M34OYQLS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.07048&json=true","fetch_graph":"https://pith.science/api/pith-number/M34OYQLSVPBEOKHDBAPD6DGVM7/graph.json","fetch_events":"https://pith.science/api/pith-number/M34OYQLSVPBEOKHDBAPD6DGVM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M34OYQLSVPBEOKHDBAPD6DGVM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M34OYQLSVPBEOKHDBAPD6DGVM7/action/storage_attestation","attest_author":"https://pith.science/pith/M34OYQLSVPBEOKHDBAPD6DGVM7/action/author_attestation","sign_citation":"https://pith.science/pith/M34OYQLSVPBEOKHDBAPD6DGVM7/action/citation_signature","submit_replication":"https://pith.science/pith/M34OYQLSVPBEOKHDBAPD6DGVM7/action/replication_record"}},"created_at":"2026-07-05T09:05:44.855991+00:00","updated_at":"2026-07-05T09:05:44.855991+00:00"}