{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IIAFWVPS5T7K7TXT6UQUJALWKF","short_pith_number":"pith:IIAFWVPS","schema_version":"1.0","canonical_sha256":"42005b55f2ecfeafcef3f5214481765173417bc61a9f283760bc7d0a022f5a40","source":{"kind":"arxiv","id":"2606.17020","version":2},"attestation_state":"computed","paper":{"title":"FusionRS: A Large-Scale RGB-Infrared-Style Remote Sensing Dataset for Cross-Modal Vision-Language Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ben Zhang, Chengyin Hu, Dingyi Lu, Fengyu Zhang, Jiaju Han, Jiujiang Guo, Luwei Yang, Qike Zhang, Xuemeng Sun, Yiwei Wei, Yuxian Dong","submitted_at":"2026-06-15T17:49:34Z","abstract_excerpt":"Remote sensing vision-language models have advanced Earth observation, but available large-scale vision-language resources remain RGB-centered, leaving complementary infrared information underexplored. Infrared observations provide distinctive intensity structures, object boundaries, and illumination-invariant cues that complement conventional RGB imagery, yet large-scale RGB-infrared-text resources remain scarce. We introduce FusionRS, the first large-scale RGB-infrared-style-text dataset for controlled dual-modal remote sensing vision-language learning. It contains 600,000 spatially aligned "},"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":"2606.17020","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-15T17:49:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6d0414212e208ba3fe8c05601aa4661674d6aa0b4e090fa759ebe49e201d2d03","abstract_canon_sha256":"3bf360a06c5cd1bbd6950ed470b766f006ff49275418b1adff08802d7531509f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:00:33.077832Z","signature_b64":"Lwxmzj/9xiwxm5pJ1rjarotOTnCf16/2KIi5hKK6uWgfh0cwGGBWUw2rDHJac6kZ2S6dJqDiA29plBQoQ+8hBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42005b55f2ecfeafcef3f5214481765173417bc61a9f283760bc7d0a022f5a40","last_reissued_at":"2026-08-04T02:00:33.075917Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:00:33.075917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FusionRS: A Large-Scale RGB-Infrared-Style Remote Sensing Dataset for Cross-Modal Vision-Language Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ben Zhang, Chengyin Hu, Dingyi Lu, Fengyu Zhang, Jiaju Han, Jiujiang Guo, Luwei Yang, Qike Zhang, Xuemeng Sun, Yiwei Wei, Yuxian Dong","submitted_at":"2026-06-15T17:49:34Z","abstract_excerpt":"Remote sensing vision-language models have advanced Earth observation, but available large-scale vision-language resources remain RGB-centered, leaving complementary infrared information underexplored. Infrared observations provide distinctive intensity structures, object boundaries, and illumination-invariant cues that complement conventional RGB imagery, yet large-scale RGB-infrared-text resources remain scarce. We introduce FusionRS, the first large-scale RGB-infrared-style-text dataset for controlled dual-modal remote sensing vision-language learning. It contains 600,000 spatially aligned "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17020","kind":"arxiv","version":2},"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/2606.17020/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":"2606.17020","created_at":"2026-08-04T02:00:33.077549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17020v2","created_at":"2026-08-04T02:00:33.077549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17020","created_at":"2026-08-04T02:00:33.077549+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIAFWVPS5T7K","created_at":"2026-08-04T02:00:33.077549+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIAFWVPS5T7K7TXT","created_at":"2026-08-04T02:00:33.077549+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIAFWVPS","created_at":"2026-08-04T02:00:33.077549+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06552","citing_title":"MonoIR-RS: Infrared Remote Sensing Vision-Language Learning with CLIP and VLM Adaptation","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IIAFWVPS5T7K7TXT6UQUJALWKF","json":"https://pith.science/pith/IIAFWVPS5T7K7TXT6UQUJALWKF.json","graph_json":"https://pith.science/api/pith-number/IIAFWVPS5T7K7TXT6UQUJALWKF/graph.json","events_json":"https://pith.science/api/pith-number/IIAFWVPS5T7K7TXT6UQUJALWKF/events.json","paper":"https://pith.science/paper/IIAFWVPS"},"agent_actions":{"view_html":"https://pith.science/pith/IIAFWVPS5T7K7TXT6UQUJALWKF","download_json":"https://pith.science/pith/IIAFWVPS5T7K7TXT6UQUJALWKF.json","view_paper":"https://pith.science/paper/IIAFWVPS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17020&json=true","fetch_graph":"https://pith.science/api/pith-number/IIAFWVPS5T7K7TXT6UQUJALWKF/graph.json","fetch_events":"https://pith.science/api/pith-number/IIAFWVPS5T7K7TXT6UQUJALWKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIAFWVPS5T7K7TXT6UQUJALWKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIAFWVPS5T7K7TXT6UQUJALWKF/action/storage_attestation","attest_author":"https://pith.science/pith/IIAFWVPS5T7K7TXT6UQUJALWKF/action/author_attestation","sign_citation":"https://pith.science/pith/IIAFWVPS5T7K7TXT6UQUJALWKF/action/citation_signature","submit_replication":"https://pith.science/pith/IIAFWVPS5T7K7TXT6UQUJALWKF/action/replication_record"}},"created_at":"2026-08-04T02:00:33.077549+00:00","updated_at":"2026-08-04T02:00:33.077549+00:00"}