{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FRNMXIYQ4453CGTOOH4MPPTKJS","short_pith_number":"pith:FRNMXIYQ","schema_version":"1.0","canonical_sha256":"2c5acba310e73bb11a6e71f8c7be6a4caa28d03c5bc6d81cf04623309dc836a5","source":{"kind":"arxiv","id":"2502.12987","version":1},"attestation_state":"computed","paper":{"title":"Ensemble Kalman filter in latent space using a variational autoencoder pair","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Alberto Carrassi, Ivo Pasmans, Marc Bocquet, Tobias Sebastian Finn, Yumeng Chen","submitted_at":"2025-02-18T16:11:05Z","abstract_excerpt":"Popular (ensemble) Kalman filter data assimilation (DA) approaches assume that the errors in both the a priori estimate of the state and those in the observations are Gaussian. For constrained variables, e.g. sea ice concentration or stress, such an assumption does not hold. The variational autoencoder (VAE) is a machine learning (ML) technique that allows to map an arbitrary distribution to/from a latent space in which the distribution is supposedly closer to a Gaussian. We propose a novel hybrid DA-ML approach in which VAEs are incorporated in the DA procedure. Specifically, we introduce a v"},"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":"2502.12987","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-18T16:11:05Z","cross_cats_sorted":["physics.ao-ph"],"title_canon_sha256":"c8675c5b4a3c6eb53c61ffb1b16a5e7c34ac824cb4b085509087c4c13f03fdd4","abstract_canon_sha256":"d270e5080aaa6c43d29b943684d0c616cb7e5f330a7bc91e9fd62013a4a6b02f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:27.595990Z","signature_b64":"+TK+eulsOLfB5kuhH65/gdu5tJmVp8FQ9lFk6whD/fhS6Y1bTKanIQhFhKmofLTUtpbnyXz2wx+8RMZb8/4QCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c5acba310e73bb11a6e71f8c7be6a4caa28d03c5bc6d81cf04623309dc836a5","last_reissued_at":"2026-07-05T10:16:27.595488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:27.595488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ensemble Kalman filter in latent space using a variational autoencoder pair","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Alberto Carrassi, Ivo Pasmans, Marc Bocquet, Tobias Sebastian Finn, Yumeng Chen","submitted_at":"2025-02-18T16:11:05Z","abstract_excerpt":"Popular (ensemble) Kalman filter data assimilation (DA) approaches assume that the errors in both the a priori estimate of the state and those in the observations are Gaussian. For constrained variables, e.g. sea ice concentration or stress, such an assumption does not hold. The variational autoencoder (VAE) is a machine learning (ML) technique that allows to map an arbitrary distribution to/from a latent space in which the distribution is supposedly closer to a Gaussian. We propose a novel hybrid DA-ML approach in which VAEs are incorporated in the DA procedure. Specifically, we introduce a v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12987","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/2502.12987/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":"2502.12987","created_at":"2026-07-05T10:16:27.595556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12987v1","created_at":"2026-07-05T10:16:27.595556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12987","created_at":"2026-07-05T10:16:27.595556+00:00"},{"alias_kind":"pith_short_12","alias_value":"FRNMXIYQ4453","created_at":"2026-07-05T10:16:27.595556+00:00"},{"alias_kind":"pith_short_16","alias_value":"FRNMXIYQ4453CGTO","created_at":"2026-07-05T10:16:27.595556+00:00"},{"alias_kind":"pith_short_8","alias_value":"FRNMXIYQ","created_at":"2026-07-05T10:16:27.595556+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02889","citing_title":"Rethinking Forward Processes for Score-Based Nonlinear Data Assimilation in High Dimensions","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02889","citing_title":"Rethinking Forward Processes for Score-Based Nonlinear Data Assimilation in High Dimensions","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FRNMXIYQ4453CGTOOH4MPPTKJS","json":"https://pith.science/pith/FRNMXIYQ4453CGTOOH4MPPTKJS.json","graph_json":"https://pith.science/api/pith-number/FRNMXIYQ4453CGTOOH4MPPTKJS/graph.json","events_json":"https://pith.science/api/pith-number/FRNMXIYQ4453CGTOOH4MPPTKJS/events.json","paper":"https://pith.science/paper/FRNMXIYQ"},"agent_actions":{"view_html":"https://pith.science/pith/FRNMXIYQ4453CGTOOH4MPPTKJS","download_json":"https://pith.science/pith/FRNMXIYQ4453CGTOOH4MPPTKJS.json","view_paper":"https://pith.science/paper/FRNMXIYQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12987&json=true","fetch_graph":"https://pith.science/api/pith-number/FRNMXIYQ4453CGTOOH4MPPTKJS/graph.json","fetch_events":"https://pith.science/api/pith-number/FRNMXIYQ4453CGTOOH4MPPTKJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FRNMXIYQ4453CGTOOH4MPPTKJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FRNMXIYQ4453CGTOOH4MPPTKJS/action/storage_attestation","attest_author":"https://pith.science/pith/FRNMXIYQ4453CGTOOH4MPPTKJS/action/author_attestation","sign_citation":"https://pith.science/pith/FRNMXIYQ4453CGTOOH4MPPTKJS/action/citation_signature","submit_replication":"https://pith.science/pith/FRNMXIYQ4453CGTOOH4MPPTKJS/action/replication_record"}},"created_at":"2026-07-05T10:16:27.595556+00:00","updated_at":"2026-07-05T10:16:27.595556+00:00"}