{"paper":{"title":"A Multi-Agent Feedback System for Detecting and Describing News Events in Satellite Imagery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A multi-agent feedback system detects and describes five times more news events in satellite imagery than traditional geocoding.","cross_cats":["cs.MA"],"primary_cat":"cs.CV","authors_text":"Ash Hoover, Kerri Cahoy, Madeline Anderson, Mikhail Klassen","submitted_at":"2026-04-14T14:12:19Z","abstract_excerpt":"Changes in satellite imagery often occur over multiple time steps. Despite the emergence of bi-temporal change captioning datasets, there is a lack of multi-temporal event captioning datasets (at least two images per sequence) in remote sensing. This gap exists because (1) searching for visible events in satellite imagery and (2) labeling multi-temporal sequences require significant time and labor. To address these challenges, we present SkyScraper, an iterative multi-agent workflow that geocodes news articles and synthesizes captions for corresponding satellite image sequences. Our experiment"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our experiments show that SkyScraper successfully finds 5x more events than traditional geocoding methods, demonstrating that agentic feedback is an effective strategy for surfacing new multi-temporal events in satellite imagery.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the multi-agent system can accurately geocode news events to visible changes in satellite imagery sequences and generate reliable captions without high rates of false positives or incorrect descriptions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SkyScraper uses iterative multi-agent feedback to geocode news articles and synthesize captions for satellite image sequences, locating 5x more events than traditional methods and producing a new 5,000-sequence dataset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A multi-agent feedback system detects and describes five times more news events in satellite imagery than traditional geocoding.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"bee6f0e985df72c71150d8024dafea57d89b9e8293b98010efad524baf10ed48"},"source":{"id":"2604.12772","kind":"arxiv","version":2},"verdict":{"id":"a18da291-8da2-4e1c-8d14-8b7bcf954828","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T14:56:12.193403Z","strongest_claim":"Our experiments show that SkyScraper successfully finds 5x more events than traditional geocoding methods, demonstrating that agentic feedback is an effective strategy for surfacing new multi-temporal events in satellite imagery.","one_line_summary":"SkyScraper uses iterative multi-agent feedback to geocode news articles and synthesize captions for satellite image sequences, locating 5x more events than traditional methods and producing a new 5,000-sequence dataset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the multi-agent system can accurately geocode news events to visible changes in satellite imagery sequences and generate reliable captions without high rates of false positives or incorrect descriptions.","pith_extraction_headline":"A multi-agent feedback system detects and describes five times more news events in satellite imagery than traditional geocoding."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.12772/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"}