{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:24D3KFXEW25WGLUISF3PHAUPK5","short_pith_number":"pith:24D3KFXE","schema_version":"1.0","canonical_sha256":"d707b516e4b6bb632e889176f3828f5740ebf13b039735225fb2e722c218c728","source":{"kind":"arxiv","id":"2507.20776","version":3},"attestation_state":"computed","paper":{"title":"RingMo-Agent: A Unified Remote Sensing Foundation Model for Multi-Platform and Multi-Modal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanbo Bi, Huiyang Hu, KaiWen Wei, Kaiyue Kang, Kun Fu, Mengyu Wang, Peijin Wang, Tong Ling, Wenhui Diao, Wenxin Yin, Xian Sun, Yingchao Feng","submitted_at":"2025-07-28T12:39:33Z","abstract_excerpt":"Remote sensing (RS) images from multiple modalities and platforms exhibit diverse details due to differences in sensor characteristics and imaging perspectives. Existing vision-language research in RS largely relies on relatively homogeneous data sources. Moreover, they still remain limited to conventional visual perception tasks such as classification or captioning. As a result, these methods fail to serve as a unified and standalone framework capable of effectively handling RS imagery from diverse sources in real-world applications. To address these issues, we propose RingMo-Agent, a model d"},"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":"2507.20776","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-28T12:39:33Z","cross_cats_sorted":[],"title_canon_sha256":"c6293be69516fdb230e80c0b6bb8c6e639fe1e7e39ef8b96ce1c2079b7cc92a4","abstract_canon_sha256":"4b1ef28e0fd56666c2fcf0a2e3042992ea84fe870f30bd2545d03520a18ce683"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-18T02:15:36.440936Z","signature_b64":"S5hycZCo0kMNUjl7MKdgYCx4QsLxe3rr+yUiCRZIqNgls9Gaz5NH1RsMHlP9E36/rK5e3fVa6ILc4Vlpeny8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d707b516e4b6bb632e889176f3828f5740ebf13b039735225fb2e722c218c728","last_reissued_at":"2026-08-18T02:15:36.439297Z","signature_status":"signed_v1","first_computed_at":"2026-08-18T02:15:36.439297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RingMo-Agent: A Unified Remote Sensing Foundation Model for Multi-Platform and Multi-Modal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanbo Bi, Huiyang Hu, KaiWen Wei, Kaiyue Kang, Kun Fu, Mengyu Wang, Peijin Wang, Tong Ling, Wenhui Diao, Wenxin Yin, Xian Sun, Yingchao Feng","submitted_at":"2025-07-28T12:39:33Z","abstract_excerpt":"Remote sensing (RS) images from multiple modalities and platforms exhibit diverse details due to differences in sensor characteristics and imaging perspectives. Existing vision-language research in RS largely relies on relatively homogeneous data sources. Moreover, they still remain limited to conventional visual perception tasks such as classification or captioning. As a result, these methods fail to serve as a unified and standalone framework capable of effectively handling RS imagery from diverse sources in real-world applications. To address these issues, we propose RingMo-Agent, a model d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20776","kind":"arxiv","version":3},"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/2507.20776/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":"2507.20776","created_at":"2026-08-18T02:15:36.438915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.20776v3","created_at":"2026-08-18T02:15:36.438915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20776","created_at":"2026-08-18T02:15:36.438915+00:00"},{"alias_kind":"pith_short_12","alias_value":"24D3KFXEW25W","created_at":"2026-08-18T02:15:36.438915+00:00"},{"alias_kind":"pith_short_16","alias_value":"24D3KFXEW25WGLUI","created_at":"2026-08-18T02:15:36.438915+00:00"},{"alias_kind":"pith_short_8","alias_value":"24D3KFXE","created_at":"2026-08-18T02:15:36.438915+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2607.01050","citing_title":"GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervision","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2606.31745","citing_title":"JL1-CC&QA: Extending the JL1-CD Benchmark with Change Captioning and Question Answering","ref_index":138,"is_internal_anchor":true},{"citing_arxiv_id":"2601.01891","citing_title":"Agentic AI in Remote Sensing: Foundations, Taxonomy, and Emerging Systems","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12678","citing_title":"No One Knows the State of the Art in Geospatial Foundation Models","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10769","citing_title":"MPerS: Dynamic MLLM MixExperts Perception-Guided Remote Sensing Scene Segmentation","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04777","citing_title":"Bridging Perception and Action: A Lightweight Multimodal Meta-Planner Framework for Robust Earth Observation Agents","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10591","citing_title":"GeoMeld: Toward Semantically Grounded Foundation Models for Remote Sensing","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/24D3KFXEW25WGLUISF3PHAUPK5","json":"https://pith.science/pith/24D3KFXEW25WGLUISF3PHAUPK5.json","graph_json":"https://pith.science/api/pith-number/24D3KFXEW25WGLUISF3PHAUPK5/graph.json","events_json":"https://pith.science/api/pith-number/24D3KFXEW25WGLUISF3PHAUPK5/events.json","paper":"https://pith.science/paper/24D3KFXE"},"agent_actions":{"view_html":"https://pith.science/pith/24D3KFXEW25WGLUISF3PHAUPK5","download_json":"https://pith.science/pith/24D3KFXEW25WGLUISF3PHAUPK5.json","view_paper":"https://pith.science/paper/24D3KFXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.20776&json=true","fetch_graph":"https://pith.science/api/pith-number/24D3KFXEW25WGLUISF3PHAUPK5/graph.json","fetch_events":"https://pith.science/api/pith-number/24D3KFXEW25WGLUISF3PHAUPK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24D3KFXEW25WGLUISF3PHAUPK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24D3KFXEW25WGLUISF3PHAUPK5/action/storage_attestation","attest_author":"https://pith.science/pith/24D3KFXEW25WGLUISF3PHAUPK5/action/author_attestation","sign_citation":"https://pith.science/pith/24D3KFXEW25WGLUISF3PHAUPK5/action/citation_signature","submit_replication":"https://pith.science/pith/24D3KFXEW25WGLUISF3PHAUPK5/action/replication_record"}},"created_at":"2026-08-18T02:15:36.438915+00:00","updated_at":"2026-08-18T02:15:36.438915+00:00"}