{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OWLNSEGOXNLKX4KF7XGKYAFM7M","short_pith_number":"pith:OWLNSEGO","schema_version":"1.0","canonical_sha256":"7596d910cebb56abf145fdccac00acfb126f1ad3a9390c4a1eedb0983da7b5c7","source":{"kind":"arxiv","id":"2509.10919","version":1},"attestation_state":"computed","paper":{"title":"Lightweight Metadata-Aware Mixture-of-Experts Masked Autoencoder for Earth Observation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Mohanad Albughdadi","submitted_at":"2025-09-13T17:35:17Z","abstract_excerpt":"Recent advances in Earth Observation have focused on large-scale foundation models. However, these models are computationally expensive, limiting their accessibility and reuse for downstream tasks. In this work, we investigate compact architectures as a practical pathway toward smaller general-purpose EO models. We propose a Metadata-aware Mixture-of-Experts Masked Autoencoder (MoE-MAE) with only 2.5M parameters. The model combines sparse expert routing with geo-temporal conditioning, incorporating imagery alongside latitude/longitude and seasonal/daily cyclic encodings. We pretrain the MoE-MA"},"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":"2509.10919","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-13T17:35:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fdedab1ae1ab1ac03fe696909cd48e079d31979c750f6e113c21ccc88393cebd","abstract_canon_sha256":"3ca10817a27757d14de393925378ebbe69cb35da956279e81f73827115c8946c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:30.378881Z","signature_b64":"//REA1CpDipj84WE2sjTCLVw0ZXUf5Kds1jke/mP34UPeGDyCGgsw0iIrEic+2nKUGLKUFPcS/jzkFT5jojzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7596d910cebb56abf145fdccac00acfb126f1ad3a9390c4a1eedb0983da7b5c7","last_reissued_at":"2026-07-05T12:11:30.378414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:30.378414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lightweight Metadata-Aware Mixture-of-Experts Masked Autoencoder for Earth Observation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Mohanad Albughdadi","submitted_at":"2025-09-13T17:35:17Z","abstract_excerpt":"Recent advances in Earth Observation have focused on large-scale foundation models. However, these models are computationally expensive, limiting their accessibility and reuse for downstream tasks. In this work, we investigate compact architectures as a practical pathway toward smaller general-purpose EO models. We propose a Metadata-aware Mixture-of-Experts Masked Autoencoder (MoE-MAE) with only 2.5M parameters. The model combines sparse expert routing with geo-temporal conditioning, incorporating imagery alongside latitude/longitude and seasonal/daily cyclic encodings. We pretrain the MoE-MA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.10919","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/2509.10919/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":"2509.10919","created_at":"2026-07-05T12:11:30.378469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.10919v1","created_at":"2026-07-05T12:11:30.378469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.10919","created_at":"2026-07-05T12:11:30.378469+00:00"},{"alias_kind":"pith_short_12","alias_value":"OWLNSEGOXNLK","created_at":"2026-07-05T12:11:30.378469+00:00"},{"alias_kind":"pith_short_16","alias_value":"OWLNSEGOXNLKX4KF","created_at":"2026-07-05T12:11:30.378469+00:00"},{"alias_kind":"pith_short_8","alias_value":"OWLNSEGO","created_at":"2026-07-05T12:11:30.378469+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/OWLNSEGOXNLKX4KF7XGKYAFM7M","json":"https://pith.science/pith/OWLNSEGOXNLKX4KF7XGKYAFM7M.json","graph_json":"https://pith.science/api/pith-number/OWLNSEGOXNLKX4KF7XGKYAFM7M/graph.json","events_json":"https://pith.science/api/pith-number/OWLNSEGOXNLKX4KF7XGKYAFM7M/events.json","paper":"https://pith.science/paper/OWLNSEGO"},"agent_actions":{"view_html":"https://pith.science/pith/OWLNSEGOXNLKX4KF7XGKYAFM7M","download_json":"https://pith.science/pith/OWLNSEGOXNLKX4KF7XGKYAFM7M.json","view_paper":"https://pith.science/paper/OWLNSEGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.10919&json=true","fetch_graph":"https://pith.science/api/pith-number/OWLNSEGOXNLKX4KF7XGKYAFM7M/graph.json","fetch_events":"https://pith.science/api/pith-number/OWLNSEGOXNLKX4KF7XGKYAFM7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OWLNSEGOXNLKX4KF7XGKYAFM7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OWLNSEGOXNLKX4KF7XGKYAFM7M/action/storage_attestation","attest_author":"https://pith.science/pith/OWLNSEGOXNLKX4KF7XGKYAFM7M/action/author_attestation","sign_citation":"https://pith.science/pith/OWLNSEGOXNLKX4KF7XGKYAFM7M/action/citation_signature","submit_replication":"https://pith.science/pith/OWLNSEGOXNLKX4KF7XGKYAFM7M/action/replication_record"}},"created_at":"2026-07-05T12:11:30.378469+00:00","updated_at":"2026-07-05T12:11:30.378469+00:00"}