{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X5A3WVD5LL6JQYTODE3AYAZIDM","short_pith_number":"pith:X5A3WVD5","schema_version":"1.0","canonical_sha256":"bf41bb547d5afc98626e19360c03281b203afd6641e31a9e6f858bab137db42a","source":{"kind":"arxiv","id":"2502.17066","version":2},"attestation_state":"computed","paper":{"title":"DUNIA: Pixel-Sized Embeddings via Cross-Modal Alignment for Earth Observation Applications","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexandre d'Aspremont, Aurelien De Truchis, Fabian Gieseke, Gabriel Belouze, Ibrahim Fayad, Martin Schwartz, Max Zimmer, Philippe Ciais, Sarah Brood","submitted_at":"2025-02-24T11:28:00Z","abstract_excerpt":"Significant efforts have been directed towards adapting self-supervised multimodal learning for Earth observation applications. However, most current methods produce coarse patch-sized embeddings, limiting their effectiveness and integration with other modalities like LiDAR. To close this gap, we present DUNIA, an approach to learn pixel-sized embeddings through cross-modal alignment between images and full-waveform LiDAR data. As the model is trained in a contrastive manner, the embeddings can be directly leveraged in the context of a variety of environmental monitoring tasks in a zero-shot s"},"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":"2502.17066","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-24T11:28:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"01d98df9654899943277ef4306c9fb2da9f76eaa7b93528dfb9af29dd50d76d2","abstract_canon_sha256":"42344c8abbb76ea8014775535da2fc7ecdf63d03126268ab3353df66fe5e7e46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:04.965068Z","signature_b64":"JeCUL9Yl/sfpZRi0vzZpBthVULhdwmuxlCKucmdQKLO/pOFAPeB5qYdq+kWZFrt3YAMbXzbv7F6RUQ6hOqw6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf41bb547d5afc98626e19360c03281b203afd6641e31a9e6f858bab137db42a","last_reissued_at":"2026-07-05T11:38:04.964530Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:04.964530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DUNIA: Pixel-Sized Embeddings via Cross-Modal Alignment for Earth Observation Applications","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexandre d'Aspremont, Aurelien De Truchis, Fabian Gieseke, Gabriel Belouze, Ibrahim Fayad, Martin Schwartz, Max Zimmer, Philippe Ciais, Sarah Brood","submitted_at":"2025-02-24T11:28:00Z","abstract_excerpt":"Significant efforts have been directed towards adapting self-supervised multimodal learning for Earth observation applications. However, most current methods produce coarse patch-sized embeddings, limiting their effectiveness and integration with other modalities like LiDAR. To close this gap, we present DUNIA, an approach to learn pixel-sized embeddings through cross-modal alignment between images and full-waveform LiDAR data. As the model is trained in a contrastive manner, the embeddings can be directly leveraged in the context of a variety of environmental monitoring tasks in a zero-shot s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17066","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/2502.17066/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":"2502.17066","created_at":"2026-07-05T11:38:04.964581+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.17066v2","created_at":"2026-07-05T11:38:04.964581+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17066","created_at":"2026-07-05T11:38:04.964581+00:00"},{"alias_kind":"pith_short_12","alias_value":"X5A3WVD5LL6J","created_at":"2026-07-05T11:38:04.964581+00:00"},{"alias_kind":"pith_short_16","alias_value":"X5A3WVD5LL6JQYTO","created_at":"2026-07-05T11:38:04.964581+00:00"},{"alias_kind":"pith_short_8","alias_value":"X5A3WVD5","created_at":"2026-07-05T11:38:04.964581+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/X5A3WVD5LL6JQYTODE3AYAZIDM","json":"https://pith.science/pith/X5A3WVD5LL6JQYTODE3AYAZIDM.json","graph_json":"https://pith.science/api/pith-number/X5A3WVD5LL6JQYTODE3AYAZIDM/graph.json","events_json":"https://pith.science/api/pith-number/X5A3WVD5LL6JQYTODE3AYAZIDM/events.json","paper":"https://pith.science/paper/X5A3WVD5"},"agent_actions":{"view_html":"https://pith.science/pith/X5A3WVD5LL6JQYTODE3AYAZIDM","download_json":"https://pith.science/pith/X5A3WVD5LL6JQYTODE3AYAZIDM.json","view_paper":"https://pith.science/paper/X5A3WVD5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.17066&json=true","fetch_graph":"https://pith.science/api/pith-number/X5A3WVD5LL6JQYTODE3AYAZIDM/graph.json","fetch_events":"https://pith.science/api/pith-number/X5A3WVD5LL6JQYTODE3AYAZIDM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X5A3WVD5LL6JQYTODE3AYAZIDM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X5A3WVD5LL6JQYTODE3AYAZIDM/action/storage_attestation","attest_author":"https://pith.science/pith/X5A3WVD5LL6JQYTODE3AYAZIDM/action/author_attestation","sign_citation":"https://pith.science/pith/X5A3WVD5LL6JQYTODE3AYAZIDM/action/citation_signature","submit_replication":"https://pith.science/pith/X5A3WVD5LL6JQYTODE3AYAZIDM/action/replication_record"}},"created_at":"2026-07-05T11:38:04.964581+00:00","updated_at":"2026-07-05T11:38:04.964581+00:00"}