{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HJAA5WK3GTY3J4UE34GN75V4QA","short_pith_number":"pith:HJAA5WK3","schema_version":"1.0","canonical_sha256":"3a400ed95b34f1b4f284df0cdff6bc802c4aeb293c08b0a35b6a72a28cd8131a","source":{"kind":"arxiv","id":"2505.14951","version":1},"attestation_state":"computed","paper":{"title":"MultiMAE Meets Earth Observation: Pre-training Multi-modal Multi-task Masked Autoencoders for Earth Observation Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anis Kacem, Danila Rukhovich, Djamila Aouada, Jose Sosa","submitted_at":"2025-05-20T22:24:36Z","abstract_excerpt":"Multi-modal data in Earth Observation (EO) presents a huge opportunity for improving transfer learning capabilities when pre-training deep learning models. Unlike prior work that often overlooks multi-modal EO data, recent methods have started to include it, resulting in more effective pre-training strategies. However, existing approaches commonly face challenges in effectively transferring learning to downstream tasks where the structure of available data differs from that used during pre-training. This paper addresses this limitation by exploring a more flexible multi-modal, multi-task pre-t"},"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":"2505.14951","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T22:24:36Z","cross_cats_sorted":[],"title_canon_sha256":"443e1ff5b017248e671b1e44776b74188790a0af69a7177416059cd740d0a5da","abstract_canon_sha256":"dc2cc060126467581df77409f456a058b6ba6b3bfcbada2facfbc6cce945cd94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:38.127549Z","signature_b64":"Iffi6Lhg+5ANEUxCmKGDfSIlZlcP5uFEYNx0ZBeo6pSDMeiGFaoC8TuFe7zdoeFnf7SYF4yxn+ucxbygu+kABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a400ed95b34f1b4f284df0cdff6bc802c4aeb293c08b0a35b6a72a28cd8131a","last_reissued_at":"2026-07-05T11:06:38.127075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:38.127075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MultiMAE Meets Earth Observation: Pre-training Multi-modal Multi-task Masked Autoencoders for Earth Observation Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anis Kacem, Danila Rukhovich, Djamila Aouada, Jose Sosa","submitted_at":"2025-05-20T22:24:36Z","abstract_excerpt":"Multi-modal data in Earth Observation (EO) presents a huge opportunity for improving transfer learning capabilities when pre-training deep learning models. Unlike prior work that often overlooks multi-modal EO data, recent methods have started to include it, resulting in more effective pre-training strategies. However, existing approaches commonly face challenges in effectively transferring learning to downstream tasks where the structure of available data differs from that used during pre-training. This paper addresses this limitation by exploring a more flexible multi-modal, multi-task pre-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14951","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/2505.14951/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":"2505.14951","created_at":"2026-07-05T11:06:38.127133+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14951v1","created_at":"2026-07-05T11:06:38.127133+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14951","created_at":"2026-07-05T11:06:38.127133+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJAA5WK3GTY3","created_at":"2026-07-05T11:06:38.127133+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJAA5WK3GTY3J4UE","created_at":"2026-07-05T11:06:38.127133+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJAA5WK3","created_at":"2026-07-05T11:06:38.127133+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.13385","citing_title":"Using Multiple Input Modalities Can Improve Data-Efficiency and O.O.D. Generalization for ML with Satellite Imagery","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HJAA5WK3GTY3J4UE34GN75V4QA","json":"https://pith.science/pith/HJAA5WK3GTY3J4UE34GN75V4QA.json","graph_json":"https://pith.science/api/pith-number/HJAA5WK3GTY3J4UE34GN75V4QA/graph.json","events_json":"https://pith.science/api/pith-number/HJAA5WK3GTY3J4UE34GN75V4QA/events.json","paper":"https://pith.science/paper/HJAA5WK3"},"agent_actions":{"view_html":"https://pith.science/pith/HJAA5WK3GTY3J4UE34GN75V4QA","download_json":"https://pith.science/pith/HJAA5WK3GTY3J4UE34GN75V4QA.json","view_paper":"https://pith.science/paper/HJAA5WK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14951&json=true","fetch_graph":"https://pith.science/api/pith-number/HJAA5WK3GTY3J4UE34GN75V4QA/graph.json","fetch_events":"https://pith.science/api/pith-number/HJAA5WK3GTY3J4UE34GN75V4QA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJAA5WK3GTY3J4UE34GN75V4QA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJAA5WK3GTY3J4UE34GN75V4QA/action/storage_attestation","attest_author":"https://pith.science/pith/HJAA5WK3GTY3J4UE34GN75V4QA/action/author_attestation","sign_citation":"https://pith.science/pith/HJAA5WK3GTY3J4UE34GN75V4QA/action/citation_signature","submit_replication":"https://pith.science/pith/HJAA5WK3GTY3J4UE34GN75V4QA/action/replication_record"}},"created_at":"2026-07-05T11:06:38.127133+00:00","updated_at":"2026-07-05T11:06:38.127133+00:00"}