{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:U5RFZHJWLW2XNHXNU4ZHG7EUGN","short_pith_number":"pith:U5RFZHJW","schema_version":"1.0","canonical_sha256":"a7625c9d365db5769eeda732737c9433722388be97cd670ea69048a61303a426","source":{"kind":"arxiv","id":"2312.10115","version":2},"attestation_state":"computed","paper":{"title":"SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Dang, Dingxiang Hu, Huimei He, Jiangwei Lao, Jian Wang, Jingdong Chen, Kang Wu, Lei Yu, Liheng Zhong, Lixiang Ru, Ming Yang, Xin Guo, Yansheng Li, Yingying Zhang, Yongjun Zhang, Ziyuan Huang","submitted_at":"2023-12-15T09:57:21Z","abstract_excerpt":"Prior studies on Remote Sensing Foundation Model (RSFM) reveal immense potential towards a generic model for Earth Observation. Nevertheless, these works primarily focus on a single modality without temporal and geo-context modeling, hampering their capabilities for diverse tasks. In this study, we present SkySense, a generic billion-scale model, pre-trained on a curated multi-modal Remote Sensing Imagery (RSI) dataset with 21.5 million temporal sequences. SkySense incorporates a factorized multi-modal spatiotemporal encoder taking temporal sequences of optical and Synthetic Aperture Radar (SA"},"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":"2312.10115","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-15T09:57:21Z","cross_cats_sorted":[],"title_canon_sha256":"6d294d20ddcacd79f011603d5ca738e5711ab6891594598ad040f30cfe200e8f","abstract_canon_sha256":"c4321dbcdcff63bb23f03e9b8d5ab00e0690a0fbf8434eada118cb20e35df2cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:20.506496Z","signature_b64":"ycenElESlUzYyYZSsplugwkni1G2pEwzoRtbwndTyjze2hFbsxK6sPRt8lgc3hfipxbZ5fiGz35noMDLwSWVAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7625c9d365db5769eeda732737c9433722388be97cd670ea69048a61303a426","last_reissued_at":"2026-07-05T07:59:20.506035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:20.506035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Dang, Dingxiang Hu, Huimei He, Jiangwei Lao, Jian Wang, Jingdong Chen, Kang Wu, Lei Yu, Liheng Zhong, Lixiang Ru, Ming Yang, Xin Guo, Yansheng Li, Yingying Zhang, Yongjun Zhang, Ziyuan Huang","submitted_at":"2023-12-15T09:57:21Z","abstract_excerpt":"Prior studies on Remote Sensing Foundation Model (RSFM) reveal immense potential towards a generic model for Earth Observation. Nevertheless, these works primarily focus on a single modality without temporal and geo-context modeling, hampering their capabilities for diverse tasks. In this study, we present SkySense, a generic billion-scale model, pre-trained on a curated multi-modal Remote Sensing Imagery (RSI) dataset with 21.5 million temporal sequences. SkySense incorporates a factorized multi-modal spatiotemporal encoder taking temporal sequences of optical and Synthetic Aperture Radar (SA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10115","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/2312.10115/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":"2312.10115","created_at":"2026-07-05T07:59:20.506095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.10115v2","created_at":"2026-07-05T07:59:20.506095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10115","created_at":"2026-07-05T07:59:20.506095+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5RFZHJWLW2X","created_at":"2026-07-05T07:59:20.506095+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5RFZHJWLW2XNHXN","created_at":"2026-07-05T07:59:20.506095+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5RFZHJW","created_at":"2026-07-05T07:59:20.506095+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.13780","citing_title":"Foundation Model-Driven Semantic Change Detection in Remote Sensing Imagery","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5RFZHJWLW2XNHXNU4ZHG7EUGN","json":"https://pith.science/pith/U5RFZHJWLW2XNHXNU4ZHG7EUGN.json","graph_json":"https://pith.science/api/pith-number/U5RFZHJWLW2XNHXNU4ZHG7EUGN/graph.json","events_json":"https://pith.science/api/pith-number/U5RFZHJWLW2XNHXNU4ZHG7EUGN/events.json","paper":"https://pith.science/paper/U5RFZHJW"},"agent_actions":{"view_html":"https://pith.science/pith/U5RFZHJWLW2XNHXNU4ZHG7EUGN","download_json":"https://pith.science/pith/U5RFZHJWLW2XNHXNU4ZHG7EUGN.json","view_paper":"https://pith.science/paper/U5RFZHJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.10115&json=true","fetch_graph":"https://pith.science/api/pith-number/U5RFZHJWLW2XNHXNU4ZHG7EUGN/graph.json","fetch_events":"https://pith.science/api/pith-number/U5RFZHJWLW2XNHXNU4ZHG7EUGN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5RFZHJWLW2XNHXNU4ZHG7EUGN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5RFZHJWLW2XNHXNU4ZHG7EUGN/action/storage_attestation","attest_author":"https://pith.science/pith/U5RFZHJWLW2XNHXNU4ZHG7EUGN/action/author_attestation","sign_citation":"https://pith.science/pith/U5RFZHJWLW2XNHXNU4ZHG7EUGN/action/citation_signature","submit_replication":"https://pith.science/pith/U5RFZHJWLW2XNHXNU4ZHG7EUGN/action/replication_record"}},"created_at":"2026-07-05T07:59:20.506095+00:00","updated_at":"2026-07-05T07:59:20.506095+00:00"}