{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZE57MP73IUP2TMCFYCIL752DPL","short_pith_number":"pith:ZE57MP73","schema_version":"1.0","canonical_sha256":"c93bf63ffb451fa9b045c090bff7437aca1a77b0100ab8e544a88b97c6c88f81","source":{"kind":"arxiv","id":"2501.16254","version":1},"attestation_state":"computed","paper":{"title":"Multi-Agent Geospatial Copilots for Remote Sensing Workflows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Karatzas, Chaehong Lee, Dimitrios Stamoulis, Fuxun Yu, Heming Liao, Iraklis Anagnostopoulos, Michael Fore, Ruopu Li, Varatheepan Paramanayakam, Yanan Jian","submitted_at":"2025-01-27T17:54:31Z","abstract_excerpt":"We present GeoLLM-Squad, a geospatial Copilot that introduces the novel multi-agent paradigm to remote sensing (RS) workflows. Unlike existing single-agent approaches that rely on monolithic large language models (LLM), GeoLLM-Squad separates agentic orchestration from geospatial task-solving, by delegating RS tasks to specialized sub-agents. Built on the open-source AutoGen and GeoLLM-Engine frameworks, our work enables the modular integration of diverse applications, spanning urban monitoring, forestry protection, climate analysis, and agriculture studies. Our results demonstrate that while "},"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":"2501.16254","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-27T17:54:31Z","cross_cats_sorted":[],"title_canon_sha256":"bcaf5324a14b104da614cd0b26d2b259cbb0d63cd7766af2d04580c4a9cae6c6","abstract_canon_sha256":"f4938a04f963c9a607ec624294878ae4a2465b0d286994afd8409955568d75ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:57.568229Z","signature_b64":"SFPOSU+dRMxvVIjOyFsWf8AG8yM4cqgPb/ZXpTdaEbclfJR1S92RkAyVb9GOeeyDDeYOKIqTsNLck9JHDDlCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c93bf63ffb451fa9b045c090bff7437aca1a77b0100ab8e544a88b97c6c88f81","last_reissued_at":"2026-07-05T10:05:57.567661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:57.567661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Geospatial Copilots for Remote Sensing Workflows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Karatzas, Chaehong Lee, Dimitrios Stamoulis, Fuxun Yu, Heming Liao, Iraklis Anagnostopoulos, Michael Fore, Ruopu Li, Varatheepan Paramanayakam, Yanan Jian","submitted_at":"2025-01-27T17:54:31Z","abstract_excerpt":"We present GeoLLM-Squad, a geospatial Copilot that introduces the novel multi-agent paradigm to remote sensing (RS) workflows. Unlike existing single-agent approaches that rely on monolithic large language models (LLM), GeoLLM-Squad separates agentic orchestration from geospatial task-solving, by delegating RS tasks to specialized sub-agents. Built on the open-source AutoGen and GeoLLM-Engine frameworks, our work enables the modular integration of diverse applications, spanning urban monitoring, forestry protection, climate analysis, and agriculture studies. Our results demonstrate that while "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16254","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/2501.16254/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":"2501.16254","created_at":"2026-07-05T10:05:57.567723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16254v1","created_at":"2026-07-05T10:05:57.567723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16254","created_at":"2026-07-05T10:05:57.567723+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZE57MP73IUP2","created_at":"2026-07-05T10:05:57.567723+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZE57MP73IUP2TMCF","created_at":"2026-07-05T10:05:57.567723+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZE57MP73","created_at":"2026-07-05T10:05:57.567723+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14628","citing_title":"SmartWalkCoach: An AI Companion for End-to-End Walking Guidance, Motivation, and Reflection","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2601.01891","citing_title":"Agentic AI in Remote Sensing: Foundations, Taxonomy, and Emerging Systems","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13888","citing_title":"GeoAgentBench: A Dynamic Execution Benchmark for Tool-Augmented Agents in Spatial Analysis","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZE57MP73IUP2TMCFYCIL752DPL","json":"https://pith.science/pith/ZE57MP73IUP2TMCFYCIL752DPL.json","graph_json":"https://pith.science/api/pith-number/ZE57MP73IUP2TMCFYCIL752DPL/graph.json","events_json":"https://pith.science/api/pith-number/ZE57MP73IUP2TMCFYCIL752DPL/events.json","paper":"https://pith.science/paper/ZE57MP73"},"agent_actions":{"view_html":"https://pith.science/pith/ZE57MP73IUP2TMCFYCIL752DPL","download_json":"https://pith.science/pith/ZE57MP73IUP2TMCFYCIL752DPL.json","view_paper":"https://pith.science/paper/ZE57MP73","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16254&json=true","fetch_graph":"https://pith.science/api/pith-number/ZE57MP73IUP2TMCFYCIL752DPL/graph.json","fetch_events":"https://pith.science/api/pith-number/ZE57MP73IUP2TMCFYCIL752DPL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZE57MP73IUP2TMCFYCIL752DPL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZE57MP73IUP2TMCFYCIL752DPL/action/storage_attestation","attest_author":"https://pith.science/pith/ZE57MP73IUP2TMCFYCIL752DPL/action/author_attestation","sign_citation":"https://pith.science/pith/ZE57MP73IUP2TMCFYCIL752DPL/action/citation_signature","submit_replication":"https://pith.science/pith/ZE57MP73IUP2TMCFYCIL752DPL/action/replication_record"}},"created_at":"2026-07-05T10:05:57.567723+00:00","updated_at":"2026-07-05T10:05:57.567723+00:00"}