{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WRF7IKUNWIQX3FJBCEJQGJKWPD","short_pith_number":"pith:WRF7IKUN","schema_version":"1.0","canonical_sha256":"b44bf42a8db2217d9521111303255678d7beb03abe308da60086ba4d2daeebe6","source":{"kind":"arxiv","id":"2408.04739","version":2},"attestation_state":"computed","paper":{"title":"Accurate deep learning-based filtering for chaotic dynamics by identifying instabilities without an ensemble","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.ao-ph","stat.ML"],"primary_cat":"nlin.CD","authors_text":"Alban Farchi, Alberto Carrassi, Charlotte Durand, Ivo Pasmans, Marc Bocquet, Sibo Cheng, Tobias S. Finn, Yumeng Chen","submitted_at":"2024-08-08T19:44:57Z","abstract_excerpt":"We investigate the ability to discover data assimilation (DA) schemes meant for chaotic dynamics with deep learning. The focus is on learning the analysis step of sequential DA, from state trajectories and their observations, using a simple residual convolutional neural network, while assuming the dynamics to be known. Experiments are performed with the Lorenz 96 dynamics, which display spatiotemporal chaos and for which solid benchmarks for DA performance exist. The accuracy of the states obtained from the learned analysis approaches that of the best possibly tuned ensemble Kalman filter, and"},"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":"2408.04739","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"nlin.CD","submitted_at":"2024-08-08T19:44:57Z","cross_cats_sorted":["physics.ao-ph","stat.ML"],"title_canon_sha256":"dd09c9b8d038211a879c4b1e68a5bbc16ccf786e44f83b270ea133eff0cec4a0","abstract_canon_sha256":"6e7de268413e0678128e38bdcb3c022513704489444ca87ca2295f998093b273"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:38.812347Z","signature_b64":"0pC5vyB3tyXrIsn1Uh1zhXWTbWDtZmUaHNfMdKbLFA+1lIWnBgbsKm0PVrXEtHVjRjBEQLwS4+IPybkLN66BBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b44bf42a8db2217d9521111303255678d7beb03abe308da60086ba4d2daeebe6","last_reissued_at":"2026-07-05T09:04:38.811866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:38.811866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accurate deep learning-based filtering for chaotic dynamics by identifying instabilities without an ensemble","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.ao-ph","stat.ML"],"primary_cat":"nlin.CD","authors_text":"Alban Farchi, Alberto Carrassi, Charlotte Durand, Ivo Pasmans, Marc Bocquet, Sibo Cheng, Tobias S. Finn, Yumeng Chen","submitted_at":"2024-08-08T19:44:57Z","abstract_excerpt":"We investigate the ability to discover data assimilation (DA) schemes meant for chaotic dynamics with deep learning. The focus is on learning the analysis step of sequential DA, from state trajectories and their observations, using a simple residual convolutional neural network, while assuming the dynamics to be known. Experiments are performed with the Lorenz 96 dynamics, which display spatiotemporal chaos and for which solid benchmarks for DA performance exist. The accuracy of the states obtained from the learned analysis approaches that of the best possibly tuned ensemble Kalman filter, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04739","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/2408.04739/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":"2408.04739","created_at":"2026-07-05T09:04:38.811926+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.04739v2","created_at":"2026-07-05T09:04:38.811926+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04739","created_at":"2026-07-05T09:04:38.811926+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRF7IKUNWIQX","created_at":"2026-07-05T09:04:38.811926+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRF7IKUNWIQX3FJB","created_at":"2026-07-05T09:04:38.811926+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRF7IKUN","created_at":"2026-07-05T09:04:38.811926+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.13312","citing_title":"Tensor-Var: Efficient Four-Dimensional Variational Data Assimilation","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WRF7IKUNWIQX3FJBCEJQGJKWPD","json":"https://pith.science/pith/WRF7IKUNWIQX3FJBCEJQGJKWPD.json","graph_json":"https://pith.science/api/pith-number/WRF7IKUNWIQX3FJBCEJQGJKWPD/graph.json","events_json":"https://pith.science/api/pith-number/WRF7IKUNWIQX3FJBCEJQGJKWPD/events.json","paper":"https://pith.science/paper/WRF7IKUN"},"agent_actions":{"view_html":"https://pith.science/pith/WRF7IKUNWIQX3FJBCEJQGJKWPD","download_json":"https://pith.science/pith/WRF7IKUNWIQX3FJBCEJQGJKWPD.json","view_paper":"https://pith.science/paper/WRF7IKUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.04739&json=true","fetch_graph":"https://pith.science/api/pith-number/WRF7IKUNWIQX3FJBCEJQGJKWPD/graph.json","fetch_events":"https://pith.science/api/pith-number/WRF7IKUNWIQX3FJBCEJQGJKWPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRF7IKUNWIQX3FJBCEJQGJKWPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRF7IKUNWIQX3FJBCEJQGJKWPD/action/storage_attestation","attest_author":"https://pith.science/pith/WRF7IKUNWIQX3FJBCEJQGJKWPD/action/author_attestation","sign_citation":"https://pith.science/pith/WRF7IKUNWIQX3FJBCEJQGJKWPD/action/citation_signature","submit_replication":"https://pith.science/pith/WRF7IKUNWIQX3FJBCEJQGJKWPD/action/replication_record"}},"created_at":"2026-07-05T09:04:38.811926+00:00","updated_at":"2026-07-05T09:04:38.811926+00:00"}