{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K53KP2M2QIBZMJBWPAEPXFTOZ7","short_pith_number":"pith:K53KP2M2","schema_version":"1.0","canonical_sha256":"5776a7e99a82039624367808fb966ecfc72973746ac46377af7859dbf509273d","source":{"kind":"arxiv","id":"2502.09356","version":3},"attestation_state":"computed","paper":{"title":"Galileo: Learning Global & Local Features of Many Remote Sensing Modalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anthony Fuller, David Rolnick, Evan Shelhamer, Favyen Bastani, Gabriel Tseng, Hannah Kerner, Henry Herzog, James R. Green, Marlena Reil, Patrick Beukema","submitted_at":"2025-02-13T14:21:03Z","abstract_excerpt":"We introduce a highly multimodal transformer to represent many remote sensing modalities - multispectral optical, synthetic aperture radar, elevation, weather, pseudo-labels, and more - across space and time. These inputs are useful for diverse remote sensing tasks, such as crop mapping and flood detection. However, learning shared representations of remote sensing data is challenging, given the diversity of relevant data modalities, and because objects of interest vary massively in scale, from small boats (1-2 pixels and fast) to glaciers (thousands of pixels and slow). We present a novel sel"},"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":"2502.09356","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T14:21:03Z","cross_cats_sorted":[],"title_canon_sha256":"ba821c97705fc6ffe98e95703aee9fa9ef43224f133dfb37c4e3e3b615441ec3","abstract_canon_sha256":"4f146033725fe9a07c47997c70d95329e7e13bad45f4cf2e69c395fc7ef4e2b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:42.727174Z","signature_b64":"RMsaN/ElcStPk1SpWeFkbBzrAVq3aCC/FJu+7ZYB/Z5/cmu+8InVNAHdoKZ3AUMUCc1J0Q5jq9kxaTyFti1DAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5776a7e99a82039624367808fb966ecfc72973746ac46377af7859dbf509273d","last_reissued_at":"2026-07-05T11:15:42.726673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:42.726673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Galileo: Learning Global & Local Features of Many Remote Sensing Modalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anthony Fuller, David Rolnick, Evan Shelhamer, Favyen Bastani, Gabriel Tseng, Hannah Kerner, Henry Herzog, James R. Green, Marlena Reil, Patrick Beukema","submitted_at":"2025-02-13T14:21:03Z","abstract_excerpt":"We introduce a highly multimodal transformer to represent many remote sensing modalities - multispectral optical, synthetic aperture radar, elevation, weather, pseudo-labels, and more - across space and time. These inputs are useful for diverse remote sensing tasks, such as crop mapping and flood detection. However, learning shared representations of remote sensing data is challenging, given the diversity of relevant data modalities, and because objects of interest vary massively in scale, from small boats (1-2 pixels and fast) to glaciers (thousands of pixels and slow). We present a novel sel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09356","kind":"arxiv","version":3},"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/2502.09356/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":"2502.09356","created_at":"2026-07-05T11:15:42.726754+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.09356v3","created_at":"2026-07-05T11:15:42.726754+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09356","created_at":"2026-07-05T11:15:42.726754+00:00"},{"alias_kind":"pith_short_12","alias_value":"K53KP2M2QIBZ","created_at":"2026-07-05T11:15:42.726754+00:00"},{"alias_kind":"pith_short_16","alias_value":"K53KP2M2QIBZMJBW","created_at":"2026-07-05T11:15:42.726754+00:00"},{"alias_kind":"pith_short_8","alias_value":"K53KP2M2","created_at":"2026-07-05T11:15:42.726754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07758","citing_title":"Scalable and Trustworthy Earth Observation Foundation Models","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2506.20380","citing_title":"TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12964","citing_title":"Cross-Scale Pretraining: Enhancing Self-Supervised Learning for Low-Resolution Satellite Imagery for Semantic Segmentation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02719","citing_title":"MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K53KP2M2QIBZMJBWPAEPXFTOZ7","json":"https://pith.science/pith/K53KP2M2QIBZMJBWPAEPXFTOZ7.json","graph_json":"https://pith.science/api/pith-number/K53KP2M2QIBZMJBWPAEPXFTOZ7/graph.json","events_json":"https://pith.science/api/pith-number/K53KP2M2QIBZMJBWPAEPXFTOZ7/events.json","paper":"https://pith.science/paper/K53KP2M2"},"agent_actions":{"view_html":"https://pith.science/pith/K53KP2M2QIBZMJBWPAEPXFTOZ7","download_json":"https://pith.science/pith/K53KP2M2QIBZMJBWPAEPXFTOZ7.json","view_paper":"https://pith.science/paper/K53KP2M2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.09356&json=true","fetch_graph":"https://pith.science/api/pith-number/K53KP2M2QIBZMJBWPAEPXFTOZ7/graph.json","fetch_events":"https://pith.science/api/pith-number/K53KP2M2QIBZMJBWPAEPXFTOZ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K53KP2M2QIBZMJBWPAEPXFTOZ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K53KP2M2QIBZMJBWPAEPXFTOZ7/action/storage_attestation","attest_author":"https://pith.science/pith/K53KP2M2QIBZMJBWPAEPXFTOZ7/action/author_attestation","sign_citation":"https://pith.science/pith/K53KP2M2QIBZMJBWPAEPXFTOZ7/action/citation_signature","submit_replication":"https://pith.science/pith/K53KP2M2QIBZMJBWPAEPXFTOZ7/action/replication_record"}},"created_at":"2026-07-05T11:15:42.726754+00:00","updated_at":"2026-07-05T11:15:42.726754+00:00"}