{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UAK2PXG236EXBS3KDJKV2JPECQ","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":"62f90f00e6f9d8bd2b05182a301b82b22b9a2d1f38aa5db4c88a1ec34c71e1b3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T03:39:07Z","title_canon_sha256":"62d10a3dd88db168cdf7224ee91ad7884ead0476ef1b673ee1e9f78a68fb16fc"},"schema_version":"1.0","source":{"id":"2312.06960","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06960","created_at":"2026-07-05T07:23:12Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06960v1","created_at":"2026-07-05T07:23:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06960","created_at":"2026-07-05T07:23:12Z"},{"alias_kind":"pith_short_12","alias_value":"UAK2PXG236EX","created_at":"2026-07-05T07:23:12Z"},{"alias_kind":"pith_short_16","alias_value":"UAK2PXG236EXBS3K","created_at":"2026-07-05T07:23:12Z"},{"alias_kind":"pith_short_8","alias_value":"UAK2PXG2","created_at":"2026-07-05T07:23:12Z"}],"graph_snapshots":[{"event_id":"sha256:f430a2dbd4957004e23bf091ef661b6f43a503eab4100b38d8ccc1eb4c814ca8","target":"graph","created_at":"2026-07-05T07:23:12Z","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/2312.06960/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Bharath Hariharan, Carl Vondrick, Cheng Perng Phoo, Kavita Bala, Meilin Kelsey Liu, Utkarsh Mall","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T03:39:07Z","title":"Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06960","kind":"arxiv","version":1},"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":"sha256:07bf0bd14720c200289442f0c61eae3d2a932580249d83187a0ba8aa207d8cf9","target":"record","created_at":"2026-07-05T07:23:12Z","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":"62f90f00e6f9d8bd2b05182a301b82b22b9a2d1f38aa5db4c88a1ec34c71e1b3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T03:39:07Z","title_canon_sha256":"62d10a3dd88db168cdf7224ee91ad7884ead0476ef1b673ee1e9f78a68fb16fc"},"schema_version":"1.0","source":{"id":"2312.06960","kind":"arxiv","version":1}},"canonical_sha256":"a015a7dcdadf8970cb6a1a555d25e41431bc2fdb66e8ced5423cac98f85f7114","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a015a7dcdadf8970cb6a1a555d25e41431bc2fdb66e8ced5423cac98f85f7114","first_computed_at":"2026-07-05T07:23:12.152163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:23:12.152163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7UCSYlydTOZ5r6OiTywbeVrZD3O6YTghMiEwiHtjrRu7iOz95VpfxwpU066yPW/Q2W3+/xlzHSImWE1m8e/mDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:23:12.152578Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.06960","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07bf0bd14720c200289442f0c61eae3d2a932580249d83187a0ba8aa207d8cf9","sha256:f430a2dbd4957004e23bf091ef661b6f43a503eab4100b38d8ccc1eb4c814ca8"],"state_sha256":"5aed4a333296bb8127dc8dd18e148893edc20581c9ac3da193cae8cf5cb4f3f1"}