{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UAK2PXG236EXBS3KDJKV2JPECQ","short_pith_number":"pith:UAK2PXG2","schema_version":"1.0","canonical_sha256":"a015a7dcdadf8970cb6a1a555d25e41431bc2fdb66e8ced5423cac98f85f7114","source":{"kind":"arxiv","id":"2312.06960","version":1},"attestation_state":"computed","paper":{"title":"Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, Carl Vondrick, Cheng Perng Phoo, Kavita Bala, Meilin Kelsey Liu, Utkarsh Mall","submitted_at":"2023-12-12T03:39:07Z","abstract_excerpt":"We introduce a method to train vision-language models for remote-sensing images without using any textual annotations. Our key insight is to use co-located internet imagery taken on the ground as an intermediary for connecting remote-sensing images and language. Specifically, we train an image encoder for remote sensing images to align with the image encoder of CLIP using a large amount of paired internet and satellite images. Our unsupervised approach enables the training of a first-of-its-kind large-scale vision language model (VLM) for remote sensing images at two different resolutions. We "},"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":"2312.06960","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T03:39:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"62d10a3dd88db168cdf7224ee91ad7884ead0476ef1b673ee1e9f78a68fb16fc","abstract_canon_sha256":"62f90f00e6f9d8bd2b05182a301b82b22b9a2d1f38aa5db4c88a1ec34c71e1b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:12.152578Z","signature_b64":"7UCSYlydTOZ5r6OiTywbeVrZD3O6YTghMiEwiHtjrRu7iOz95VpfxwpU066yPW/Q2W3+/xlzHSImWE1m8e/mDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a015a7dcdadf8970cb6a1a555d25e41431bc2fdb66e8ced5423cac98f85f7114","last_reissued_at":"2026-07-05T07:23:12.152163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:12.152163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, Carl Vondrick, Cheng Perng Phoo, Kavita Bala, Meilin Kelsey Liu, Utkarsh Mall","submitted_at":"2023-12-12T03:39:07Z","abstract_excerpt":"We introduce a method to train vision-language models for remote-sensing images without using any textual annotations. Our key insight is to use co-located internet imagery taken on the ground as an intermediary for connecting remote-sensing images and language. Specifically, we train an image encoder for remote sensing images to align with the image encoder of CLIP using a large amount of paired internet and satellite images. Our unsupervised approach enables the training of a first-of-its-kind large-scale vision language model (VLM) for remote sensing images at two different resolutions. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06960","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/2312.06960/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":"2312.06960","created_at":"2026-07-05T07:23:12.152218+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.06960v1","created_at":"2026-07-05T07:23:12.152218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06960","created_at":"2026-07-05T07:23:12.152218+00:00"},{"alias_kind":"pith_short_12","alias_value":"UAK2PXG236EX","created_at":"2026-07-05T07:23:12.152218+00:00"},{"alias_kind":"pith_short_16","alias_value":"UAK2PXG236EXBS3K","created_at":"2026-07-05T07:23:12.152218+00:00"},{"alias_kind":"pith_short_8","alias_value":"UAK2PXG2","created_at":"2026-07-05T07:23:12.152218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30168","citing_title":"OmniCD: A Foundational Framework for Remote Sensing Image Change Detection Guided by Multimodal Semantics","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23144","citing_title":"SLIP-RS: Structured-Attribute Language-Image Pre-Training for Remote Sensing Object Detection","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2510.22665","citing_title":"SARVLM: A Vision Language Foundation Model for Semantic Understanding in SAR Imagery","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04017","citing_title":"Habitat Classification from Ground-Level Imagery Using Deep Neural Networks","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2508.11196","citing_title":"UAV-VL-R1: Generalizing Vision-Language Models via Supervised Fine-Tuning and Multi-Stage GRPO for UAV Visual Reasoning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2512.17492","citing_title":"MMLANDMARKS: a Cross-View Instance-Level Benchmark for Geo-Spatial Understanding","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2501.09686","citing_title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24919","citing_title":"Agentic AI for Remote Sensing: Technical Challenges and Research Directions","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24919","citing_title":"Agentic AI for Remote Sensing: Technical Challenges and Research Directions","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04777","citing_title":"Bridging Perception and Action: A Lightweight Multimodal Meta-Planner Framework for Robust Earth Observation Agents","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11415","citing_title":"Observe Less, Understand More: Cost-aware Cross-scale Observation for Remote Sensing Understanding","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13654","citing_title":"Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap","ref_index":149,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13565","citing_title":"UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensing","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20429","citing_title":"Fast-then-Fine: A Two-Stage Framework with Multi-Granular Representation for Cross-Modal Retrieval in Remote Sensing","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UAK2PXG236EXBS3KDJKV2JPECQ","json":"https://pith.science/pith/UAK2PXG236EXBS3KDJKV2JPECQ.json","graph_json":"https://pith.science/api/pith-number/UAK2PXG236EXBS3KDJKV2JPECQ/graph.json","events_json":"https://pith.science/api/pith-number/UAK2PXG236EXBS3KDJKV2JPECQ/events.json","paper":"https://pith.science/paper/UAK2PXG2"},"agent_actions":{"view_html":"https://pith.science/pith/UAK2PXG236EXBS3KDJKV2JPECQ","download_json":"https://pith.science/pith/UAK2PXG236EXBS3KDJKV2JPECQ.json","view_paper":"https://pith.science/paper/UAK2PXG2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.06960&json=true","fetch_graph":"https://pith.science/api/pith-number/UAK2PXG236EXBS3KDJKV2JPECQ/graph.json","fetch_events":"https://pith.science/api/pith-number/UAK2PXG236EXBS3KDJKV2JPECQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UAK2PXG236EXBS3KDJKV2JPECQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UAK2PXG236EXBS3KDJKV2JPECQ/action/storage_attestation","attest_author":"https://pith.science/pith/UAK2PXG236EXBS3KDJKV2JPECQ/action/author_attestation","sign_citation":"https://pith.science/pith/UAK2PXG236EXBS3KDJKV2JPECQ/action/citation_signature","submit_replication":"https://pith.science/pith/UAK2PXG236EXBS3KDJKV2JPECQ/action/replication_record"}},"created_at":"2026-07-05T07:23:12.152218+00:00","updated_at":"2026-07-05T07:23:12.152218+00:00"}