{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MUGN36AJQHO5FIVVHMOLLNVLCC","short_pith_number":"pith:MUGN36AJ","schema_version":"1.0","canonical_sha256":"650cddf80981ddd2a2b53b1cb5b6ab1096a0ba55294cceee8a686f8b7359f16a","source":{"kind":"arxiv","id":"2606.10819","version":1},"attestation_state":"computed","paper":{"title":"Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guangyao Zhou, Guanqun Wang, Hao Wang, He Chen, Jun Li, Miaoxin Cai, Tong Zhang, Wei Zhang, Yin Zhuang","submitted_at":"2026-06-09T13:01:51Z","abstract_excerpt":"RS-MLLMs enable natural-language understanding and spatial reasoning over earth observation imagery. However, existing models support only a narrow range of sensor types and tasks, yielding a fragmented view of the earth and leaving cross-modal geoscientific knowledge largely unexploited. This work presents Earth-OneVision, a 2B RS-MLLM that unifies six sensor modalities (i.e., optical, SAR, infrared, multispectral, temporal, and video) and cross-sensor fusion across 9 task categories within a single autoregressive framework. Three dedicated mechanisms address three bottlenecks. Full-Granulari"},"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":"2606.10819","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-09T13:01:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3f2fc0d18d0479d0bc71039adaa2c7d9b37ec90abe46d1f905c4f89e0512e87d","abstract_canon_sha256":"48d08ebfb939a418421896d21f61276e25d490523add269e6d16cca5fa72a134"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:42.160030Z","signature_b64":"WfnsUPBO379MurJveskPT1WCIZW+PEVv/DnlExzbiL0/641G6QeYXXlQEmTkrpo2mCsDION0OMcZhHUCuzCIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"650cddf80981ddd2a2b53b1cb5b6ab1096a0ba55294cceee8a686f8b7359f16a","last_reissued_at":"2026-06-10T01:10:42.159164Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:42.159164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guangyao Zhou, Guanqun Wang, Hao Wang, He Chen, Jun Li, Miaoxin Cai, Tong Zhang, Wei Zhang, Yin Zhuang","submitted_at":"2026-06-09T13:01:51Z","abstract_excerpt":"RS-MLLMs enable natural-language understanding and spatial reasoning over earth observation imagery. However, existing models support only a narrow range of sensor types and tasks, yielding a fragmented view of the earth and leaving cross-modal geoscientific knowledge largely unexploited. This work presents Earth-OneVision, a 2B RS-MLLM that unifies six sensor modalities (i.e., optical, SAR, infrared, multispectral, temporal, and video) and cross-sensor fusion across 9 task categories within a single autoregressive framework. Three dedicated mechanisms address three bottlenecks. Full-Granulari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10819","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/2606.10819/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":"2606.10819","created_at":"2026-06-10T01:10:42.159293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10819v1","created_at":"2026-06-10T01:10:42.159293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10819","created_at":"2026-06-10T01:10:42.159293+00:00"},{"alias_kind":"pith_short_12","alias_value":"MUGN36AJQHO5","created_at":"2026-06-10T01:10:42.159293+00:00"},{"alias_kind":"pith_short_16","alias_value":"MUGN36AJQHO5FIVV","created_at":"2026-06-10T01:10:42.159293+00:00"},{"alias_kind":"pith_short_8","alias_value":"MUGN36AJ","created_at":"2026-06-10T01:10:42.159293+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MUGN36AJQHO5FIVVHMOLLNVLCC","json":"https://pith.science/pith/MUGN36AJQHO5FIVVHMOLLNVLCC.json","graph_json":"https://pith.science/api/pith-number/MUGN36AJQHO5FIVVHMOLLNVLCC/graph.json","events_json":"https://pith.science/api/pith-number/MUGN36AJQHO5FIVVHMOLLNVLCC/events.json","paper":"https://pith.science/paper/MUGN36AJ"},"agent_actions":{"view_html":"https://pith.science/pith/MUGN36AJQHO5FIVVHMOLLNVLCC","download_json":"https://pith.science/pith/MUGN36AJQHO5FIVVHMOLLNVLCC.json","view_paper":"https://pith.science/paper/MUGN36AJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10819&json=true","fetch_graph":"https://pith.science/api/pith-number/MUGN36AJQHO5FIVVHMOLLNVLCC/graph.json","fetch_events":"https://pith.science/api/pith-number/MUGN36AJQHO5FIVVHMOLLNVLCC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MUGN36AJQHO5FIVVHMOLLNVLCC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MUGN36AJQHO5FIVVHMOLLNVLCC/action/storage_attestation","attest_author":"https://pith.science/pith/MUGN36AJQHO5FIVVHMOLLNVLCC/action/author_attestation","sign_citation":"https://pith.science/pith/MUGN36AJQHO5FIVVHMOLLNVLCC/action/citation_signature","submit_replication":"https://pith.science/pith/MUGN36AJQHO5FIVVHMOLLNVLCC/action/replication_record"}},"created_at":"2026-06-10T01:10:42.159293+00:00","updated_at":"2026-06-10T01:10:42.159293+00:00"}