{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HQGHKH4ICRYBDD2JID7AFC46TS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e1a568b8a9f0c7969e2f93dce26e699f93530e640aa345d2d3e25f4dc8d9948e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-19T15:46:41Z","title_canon_sha256":"bc1b23e11b628145d39ec0cad7050ecefb77935db43b21313efbbd008b670a9f"},"schema_version":"1.0","source":{"id":"2306.11029","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11029","created_at":"2026-07-05T08:08:17Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11029v4","created_at":"2026-07-05T08:08:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11029","created_at":"2026-07-05T08:08:17Z"},{"alias_kind":"pith_short_12","alias_value":"HQGHKH4ICRYB","created_at":"2026-07-05T08:08:17Z"},{"alias_kind":"pith_short_16","alias_value":"HQGHKH4ICRYBDD2J","created_at":"2026-07-05T08:08:17Z"},{"alias_kind":"pith_short_8","alias_value":"HQGHKH4I","created_at":"2026-07-05T08:08:17Z"}],"graph_snapshots":[{"event_id":"sha256:6863da397d2d116cec8370b47de504f16853995704090e7a437eea761aa48113","target":"graph","created_at":"2026-07-05T08:08:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.11029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Delong Chen, Fan Liu, Jiale Zhu, Jun Zhou, Liyong Fu, Qiaolin Ye, Xiaocong Zhou, Zhangqingyun Guan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-19T15:46:41Z","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11029","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:67d8fa93ea758dc43e25faa288991d82b9daa9c6ad4e965c8c112999a08d24f1","target":"record","created_at":"2026-07-05T08:08:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e1a568b8a9f0c7969e2f93dce26e699f93530e640aa345d2d3e25f4dc8d9948e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-19T15:46:41Z","title_canon_sha256":"bc1b23e11b628145d39ec0cad7050ecefb77935db43b21313efbbd008b670a9f"},"schema_version":"1.0","source":{"id":"2306.11029","kind":"arxiv","version":4}},"canonical_sha256":"3c0c751f881470118f4940fe028b9e9ca81df8ea424444b88c9296fdebe7d80f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c0c751f881470118f4940fe028b9e9ca81df8ea424444b88c9296fdebe7d80f","first_computed_at":"2026-07-05T08:08:17.150265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:17.150265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lu+J2wZpsvMT/30fuDU6QjsfoRGLiGKqHh/3zePuYOMBQgCkC2zLY2H9eJd0UTyn/jppXB7OHGMcnoKT2BdoAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:17.150741Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.11029","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67d8fa93ea758dc43e25faa288991d82b9daa9c6ad4e965c8c112999a08d24f1","sha256:6863da397d2d116cec8370b47de504f16853995704090e7a437eea761aa48113"],"state_sha256":"3c766505a52a53a048761959d13230a776fb9b752ef74fd5fc6358eba9ca5ad7"}