{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7GHXAAJI6MKOOIZVQJZUWY4TFI","short_pith_number":"pith:7GHXAAJI","schema_version":"1.0","canonical_sha256":"f98f700128f314e7233582734b63932a2b38e160ab53722ac83330a20008658b","source":{"kind":"arxiv","id":"2411.07688","version":4},"attestation_state":"computed","paper":{"title":"ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAG","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Chen, Haozhan Shen, Jianwei Yin, Tiancheng Zhao, Xu Jia, Yongheng Shang, Yuhao Wang, Yuxiang Cai, Zian Guan, Zilun Zhang","submitted_at":"2024-11-12T10:12:12Z","abstract_excerpt":"Ultra High Resolution (UHR) remote sensing imagery (RSI) (e.g. 100,000 $\\times$ 100,000 pixels or more) poses a significant challenge for current Remote Sensing Multimodal Large Language Models (RSMLLMs). If choose to resize the UHR image to standard input image size, the extensive spatial and contextual information that UHR images contain will be neglected. Otherwise, the original size of these images often exceeds the token limits of standard RSMLLMs, making it difficult to process the entire image and capture long-range dependencies to answer the query based on the abundant visual context. "},"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":"2411.07688","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T10:12:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9f17cb57c7220de44a6e42d5111a73ac407171b5b8758c6aac0151784ec5c5d5","abstract_canon_sha256":"1cc4dbf31efbe09d1ccec62b5e3f894501672eb42e079a808777d966021a9363"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:21.002973Z","signature_b64":"5mYN8OoYKAak5nepmiR2NPzb2tiZYi7Mm7pSodypATcedIInSOHhWne26WU/upfQf11PSYf36pQ3gUtjal9YCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f98f700128f314e7233582734b63932a2b38e160ab53722ac83330a20008658b","last_reissued_at":"2026-07-05T11:11:21.002477Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:21.002477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAG","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Chen, Haozhan Shen, Jianwei Yin, Tiancheng Zhao, Xu Jia, Yongheng Shang, Yuhao Wang, Yuxiang Cai, Zian Guan, Zilun Zhang","submitted_at":"2024-11-12T10:12:12Z","abstract_excerpt":"Ultra High Resolution (UHR) remote sensing imagery (RSI) (e.g. 100,000 $\\times$ 100,000 pixels or more) poses a significant challenge for current Remote Sensing Multimodal Large Language Models (RSMLLMs). If choose to resize the UHR image to standard input image size, the extensive spatial and contextual information that UHR images contain will be neglected. Otherwise, the original size of these images often exceeds the token limits of standard RSMLLMs, making it difficult to process the entire image and capture long-range dependencies to answer the query based on the abundant visual context. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07688","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/2411.07688/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":"2411.07688","created_at":"2026-07-05T11:11:21.002535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.07688v4","created_at":"2026-07-05T11:11:21.002535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07688","created_at":"2026-07-05T11:11:21.002535+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GHXAAJI6MKO","created_at":"2026-07-05T11:11:21.002535+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GHXAAJI6MKOOIZV","created_at":"2026-07-05T11:11:21.002535+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GHXAAJI","created_at":"2026-07-05T11:11:21.002535+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11122","citing_title":"Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20623","citing_title":"RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-N Ranking","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7GHXAAJI6MKOOIZVQJZUWY4TFI","json":"https://pith.science/pith/7GHXAAJI6MKOOIZVQJZUWY4TFI.json","graph_json":"https://pith.science/api/pith-number/7GHXAAJI6MKOOIZVQJZUWY4TFI/graph.json","events_json":"https://pith.science/api/pith-number/7GHXAAJI6MKOOIZVQJZUWY4TFI/events.json","paper":"https://pith.science/paper/7GHXAAJI"},"agent_actions":{"view_html":"https://pith.science/pith/7GHXAAJI6MKOOIZVQJZUWY4TFI","download_json":"https://pith.science/pith/7GHXAAJI6MKOOIZVQJZUWY4TFI.json","view_paper":"https://pith.science/paper/7GHXAAJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.07688&json=true","fetch_graph":"https://pith.science/api/pith-number/7GHXAAJI6MKOOIZVQJZUWY4TFI/graph.json","fetch_events":"https://pith.science/api/pith-number/7GHXAAJI6MKOOIZVQJZUWY4TFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GHXAAJI6MKOOIZVQJZUWY4TFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GHXAAJI6MKOOIZVQJZUWY4TFI/action/storage_attestation","attest_author":"https://pith.science/pith/7GHXAAJI6MKOOIZVQJZUWY4TFI/action/author_attestation","sign_citation":"https://pith.science/pith/7GHXAAJI6MKOOIZVQJZUWY4TFI/action/citation_signature","submit_replication":"https://pith.science/pith/7GHXAAJI6MKOOIZVQJZUWY4TFI/action/replication_record"}},"created_at":"2026-07-05T11:11:21.002535+00:00","updated_at":"2026-07-05T11:11:21.002535+00:00"}