{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HQGHKH4ICRYBDD2JID7AFC46TS","short_pith_number":"pith:HQGHKH4I","schema_version":"1.0","canonical_sha256":"3c0c751f881470118f4940fe028b9e9ca81df8ea424444b88c9296fdebe7d80f","source":{"kind":"arxiv","id":"2306.11029","version":4},"attestation_state":"computed","paper":{"title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Delong Chen, Fan Liu, Jiale Zhu, Jun Zhou, Liyong Fu, Qiaolin Ye, Xiaocong Zhou, Zhangqingyun Guan","submitted_at":"2023-06-19T15:46:41Z","abstract_excerpt":"General-purpose foundation models have led to recent breakthroughs in artificial intelligence. In remote sensing, self-supervised learning (SSL) and Masked Image Modeling (MIM) have been adopted to build foundation models. However, these models primarily learn low-level features and require annotated data for fine-tuning. Moreover, they are inapplicable for retrieval and zero-shot applications due to the lack of language understanding. To address these limitations, we propose RemoteCLIP, the first vision-language foundation model for remote sensing that aims to learn robust visual features wit"},"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":"2306.11029","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-19T15:46:41Z","cross_cats_sorted":[],"title_canon_sha256":"bc1b23e11b628145d39ec0cad7050ecefb77935db43b21313efbbd008b670a9f","abstract_canon_sha256":"e1a568b8a9f0c7969e2f93dce26e699f93530e640aa345d2d3e25f4dc8d9948e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:17.150741Z","signature_b64":"Lu+J2wZpsvMT/30fuDU6QjsfoRGLiGKqHh/3zePuYOMBQgCkC2zLY2H9eJd0UTyn/jppXB7OHGMcnoKT2BdoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c0c751f881470118f4940fe028b9e9ca81df8ea424444b88c9296fdebe7d80f","last_reissued_at":"2026-07-05T08:08:17.150265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:17.150265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Delong Chen, Fan Liu, Jiale Zhu, Jun Zhou, Liyong Fu, Qiaolin Ye, Xiaocong Zhou, Zhangqingyun Guan","submitted_at":"2023-06-19T15:46:41Z","abstract_excerpt":"General-purpose foundation models have led to recent breakthroughs in artificial intelligence. In remote sensing, self-supervised learning (SSL) and Masked Image Modeling (MIM) have been adopted to build foundation models. However, these models primarily learn low-level features and require annotated data for fine-tuning. Moreover, they are inapplicable for retrieval and zero-shot applications due to the lack of language understanding. To address these limitations, we propose RemoteCLIP, the first vision-language foundation model for remote sensing that aims to learn robust visual features wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11029","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/2306.11029/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":"2306.11029","created_at":"2026-07-05T08:08:17.150325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.11029v4","created_at":"2026-07-05T08:08:17.150325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11029","created_at":"2026-07-05T08:08:17.150325+00:00"},{"alias_kind":"pith_short_12","alias_value":"HQGHKH4ICRYB","created_at":"2026-07-05T08:08:17.150325+00:00"},{"alias_kind":"pith_short_16","alias_value":"HQGHKH4ICRYBDD2J","created_at":"2026-07-05T08:08:17.150325+00:00"},{"alias_kind":"pith_short_8","alias_value":"HQGHKH4I","created_at":"2026-07-05T08:08:17.150325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09772","citing_title":"SemDINO: A DINOv3-Driven Network for Cross-Temporal Semantic Alignment in Change Detection","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19358","citing_title":"RoofNet: A Global Multimodal Dataset for Roof Material Identification from Earth Observation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03259","citing_title":"CropVLM: A Domain-Adapted Vision-Language Model for Open-Set Crop Analysis","ref_index":34,"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":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06080","citing_title":"MSD-Score: Multi-Scale Distributional Scoring for Reference-Free Image Caption Evaluation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08956","citing_title":"Low-Data Supervised Adaptation Outperforms Prompting for Cloud Segmentation Under Domain Shift","ref_index":15,"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":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HQGHKH4ICRYBDD2JID7AFC46TS","json":"https://pith.science/pith/HQGHKH4ICRYBDD2JID7AFC46TS.json","graph_json":"https://pith.science/api/pith-number/HQGHKH4ICRYBDD2JID7AFC46TS/graph.json","events_json":"https://pith.science/api/pith-number/HQGHKH4ICRYBDD2JID7AFC46TS/events.json","paper":"https://pith.science/paper/HQGHKH4I"},"agent_actions":{"view_html":"https://pith.science/pith/HQGHKH4ICRYBDD2JID7AFC46TS","download_json":"https://pith.science/pith/HQGHKH4ICRYBDD2JID7AFC46TS.json","view_paper":"https://pith.science/paper/HQGHKH4I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.11029&json=true","fetch_graph":"https://pith.science/api/pith-number/HQGHKH4ICRYBDD2JID7AFC46TS/graph.json","fetch_events":"https://pith.science/api/pith-number/HQGHKH4ICRYBDD2JID7AFC46TS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HQGHKH4ICRYBDD2JID7AFC46TS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HQGHKH4ICRYBDD2JID7AFC46TS/action/storage_attestation","attest_author":"https://pith.science/pith/HQGHKH4ICRYBDD2JID7AFC46TS/action/author_attestation","sign_citation":"https://pith.science/pith/HQGHKH4ICRYBDD2JID7AFC46TS/action/citation_signature","submit_replication":"https://pith.science/pith/HQGHKH4ICRYBDD2JID7AFC46TS/action/replication_record"}},"created_at":"2026-07-05T08:08:17.150325+00:00","updated_at":"2026-07-05T08:08:17.150325+00:00"}