{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AIMTKV3JIS4YKGCATQLQ2JMNOL","short_pith_number":"pith:AIMTKV3J","schema_version":"1.0","canonical_sha256":"021935576944b98518409c170d258d72c714527a93275841c7b73d525625cdf8","source":{"kind":"arxiv","id":"2401.07527","version":2},"attestation_state":"computed","paper":{"title":"One for All: Toward Unified Foundation Models for Earth Vision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fahong Zhang, Xiao Xiang Zhu, Yi Wang, Zhitong Xiong","submitted_at":"2024-01-15T08:12:51Z","abstract_excerpt":"Foundation models characterized by extensive parameters and trained on large-scale datasets have demonstrated remarkable efficacy across various downstream tasks for remote sensing data. Current remote sensing foundation models typically specialize in a single modality or a specific spatial resolution range, limiting their versatility for downstream datasets. While there have been attempts to develop multi-modal remote sensing foundation models, they typically employ separate vision encoders for each modality or spatial resolution, necessitating a switch in backbones contingent upon the input "},"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":"2401.07527","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-15T08:12:51Z","cross_cats_sorted":[],"title_canon_sha256":"a715122f0aec334aca880e8831350a2e37d0e1ca2e2458fa4565bccd51592c5b","abstract_canon_sha256":"150f8cb84a8f227780da288ff6e682ce28d2fb0162acade8005c1e71607ac1d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:59.710151Z","signature_b64":"2NUdx7SnWvVC7VXJEl1MKyNR+l75AaNI2uCbegALUcD7g6vG+LM4HQJv4XoZ1HqJfdOr9PlYEBJgTud5gGSkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"021935576944b98518409c170d258d72c714527a93275841c7b73d525625cdf8","last_reissued_at":"2026-07-05T08:23:59.709696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:59.709696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One for All: Toward Unified Foundation Models for Earth Vision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fahong Zhang, Xiao Xiang Zhu, Yi Wang, Zhitong Xiong","submitted_at":"2024-01-15T08:12:51Z","abstract_excerpt":"Foundation models characterized by extensive parameters and trained on large-scale datasets have demonstrated remarkable efficacy across various downstream tasks for remote sensing data. Current remote sensing foundation models typically specialize in a single modality or a specific spatial resolution range, limiting their versatility for downstream datasets. While there have been attempts to develop multi-modal remote sensing foundation models, they typically employ separate vision encoders for each modality or spatial resolution, necessitating a switch in backbones contingent upon the input "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07527","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/2401.07527/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":"2401.07527","created_at":"2026-07-05T08:23:59.709759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.07527v2","created_at":"2026-07-05T08:23:59.709759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07527","created_at":"2026-07-05T08:23:59.709759+00:00"},{"alias_kind":"pith_short_12","alias_value":"AIMTKV3JIS4Y","created_at":"2026-07-05T08:23:59.709759+00:00"},{"alias_kind":"pith_short_16","alias_value":"AIMTKV3JIS4YKGCA","created_at":"2026-07-05T08:23:59.709759+00:00"},{"alias_kind":"pith_short_8","alias_value":"AIMTKV3J","created_at":"2026-07-05T08:23:59.709759+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.20380","citing_title":"TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AIMTKV3JIS4YKGCATQLQ2JMNOL","json":"https://pith.science/pith/AIMTKV3JIS4YKGCATQLQ2JMNOL.json","graph_json":"https://pith.science/api/pith-number/AIMTKV3JIS4YKGCATQLQ2JMNOL/graph.json","events_json":"https://pith.science/api/pith-number/AIMTKV3JIS4YKGCATQLQ2JMNOL/events.json","paper":"https://pith.science/paper/AIMTKV3J"},"agent_actions":{"view_html":"https://pith.science/pith/AIMTKV3JIS4YKGCATQLQ2JMNOL","download_json":"https://pith.science/pith/AIMTKV3JIS4YKGCATQLQ2JMNOL.json","view_paper":"https://pith.science/paper/AIMTKV3J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.07527&json=true","fetch_graph":"https://pith.science/api/pith-number/AIMTKV3JIS4YKGCATQLQ2JMNOL/graph.json","fetch_events":"https://pith.science/api/pith-number/AIMTKV3JIS4YKGCATQLQ2JMNOL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AIMTKV3JIS4YKGCATQLQ2JMNOL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AIMTKV3JIS4YKGCATQLQ2JMNOL/action/storage_attestation","attest_author":"https://pith.science/pith/AIMTKV3JIS4YKGCATQLQ2JMNOL/action/author_attestation","sign_citation":"https://pith.science/pith/AIMTKV3JIS4YKGCATQLQ2JMNOL/action/citation_signature","submit_replication":"https://pith.science/pith/AIMTKV3JIS4YKGCATQLQ2JMNOL/action/replication_record"}},"created_at":"2026-07-05T08:23:59.709759+00:00","updated_at":"2026-07-05T08:23:59.709759+00:00"}