{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MVB4AXDA6FL5CRPSUVP6S7RXAF","short_pith_number":"pith:MVB4AXDA","schema_version":"1.0","canonical_sha256":"6543c05c60f157d145f2a55fe97e3701490dd4cc5c91ec3718c9e7587b57cd40","source":{"kind":"arxiv","id":"2408.02767","version":1},"attestation_state":"computed","paper":{"title":"4D-Var using Hessian approximation and backpropagation applied to automatically-differentiable numerical and machine learning models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.DS","physics.geo-ph"],"primary_cat":"cs.LG","authors_text":"Kylen Solvik, Stephan Hoyer, Stephen G. Penny","submitted_at":"2024-08-05T18:36:13Z","abstract_excerpt":"Constraining a numerical weather prediction (NWP) model with observations via 4D variational (4D-Var) data assimilation is often difficult to implement in practice due to the need to develop and maintain a software-based tangent linear model and adjoint model. One of the most common 4D-Var algorithms uses an incremental update procedure, which has been shown to be an approximation of the Gauss-Newton method. Here we demonstrate that when using a forecast model that supports automatic differentiation, an efficient and in some cases more accurate alternative approximation of the Gauss-Newton met"},"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":"2408.02767","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-05T18:36:13Z","cross_cats_sorted":["math.DS","physics.geo-ph"],"title_canon_sha256":"93a0e68546b71a6f8d4582e2d3f6a41096321c67ebe7cef97cfb002a8f4b43f1","abstract_canon_sha256":"d6f9196ddb6922f4e83529fc163ae2385e3c6004fee1a91e18f865262af9ec43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:39.781147Z","signature_b64":"ksb0cMs2UcFlkQwX+x9b/fbcNu/rzBSyrXooPas+Qg6tr+NFryA2PZ6vXyPlUxwor7hBn2oCBUiECnILdGVxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6543c05c60f157d145f2a55fe97e3701490dd4cc5c91ec3718c9e7587b57cd40","last_reissued_at":"2026-07-05T08:52:39.780725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:39.780725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"4D-Var using Hessian approximation and backpropagation applied to automatically-differentiable numerical and machine learning models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.DS","physics.geo-ph"],"primary_cat":"cs.LG","authors_text":"Kylen Solvik, Stephan Hoyer, Stephen G. Penny","submitted_at":"2024-08-05T18:36:13Z","abstract_excerpt":"Constraining a numerical weather prediction (NWP) model with observations via 4D variational (4D-Var) data assimilation is often difficult to implement in practice due to the need to develop and maintain a software-based tangent linear model and adjoint model. One of the most common 4D-Var algorithms uses an incremental update procedure, which has been shown to be an approximation of the Gauss-Newton method. Here we demonstrate that when using a forecast model that supports automatic differentiation, an efficient and in some cases more accurate alternative approximation of the Gauss-Newton met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02767","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/2408.02767/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":"2408.02767","created_at":"2026-07-05T08:52:39.780787+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.02767v1","created_at":"2026-07-05T08:52:39.780787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02767","created_at":"2026-07-05T08:52:39.780787+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVB4AXDA6FL5","created_at":"2026-07-05T08:52:39.780787+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVB4AXDA6FL5CRPS","created_at":"2026-07-05T08:52:39.780787+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVB4AXDA","created_at":"2026-07-05T08:52:39.780787+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.00325","citing_title":"PnP-DA: Towards Principled Plug-and-Play Integration of Variational Data Assimilation and Generative Models","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVB4AXDA6FL5CRPSUVP6S7RXAF","json":"https://pith.science/pith/MVB4AXDA6FL5CRPSUVP6S7RXAF.json","graph_json":"https://pith.science/api/pith-number/MVB4AXDA6FL5CRPSUVP6S7RXAF/graph.json","events_json":"https://pith.science/api/pith-number/MVB4AXDA6FL5CRPSUVP6S7RXAF/events.json","paper":"https://pith.science/paper/MVB4AXDA"},"agent_actions":{"view_html":"https://pith.science/pith/MVB4AXDA6FL5CRPSUVP6S7RXAF","download_json":"https://pith.science/pith/MVB4AXDA6FL5CRPSUVP6S7RXAF.json","view_paper":"https://pith.science/paper/MVB4AXDA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.02767&json=true","fetch_graph":"https://pith.science/api/pith-number/MVB4AXDA6FL5CRPSUVP6S7RXAF/graph.json","fetch_events":"https://pith.science/api/pith-number/MVB4AXDA6FL5CRPSUVP6S7RXAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVB4AXDA6FL5CRPSUVP6S7RXAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVB4AXDA6FL5CRPSUVP6S7RXAF/action/storage_attestation","attest_author":"https://pith.science/pith/MVB4AXDA6FL5CRPSUVP6S7RXAF/action/author_attestation","sign_citation":"https://pith.science/pith/MVB4AXDA6FL5CRPSUVP6S7RXAF/action/citation_signature","submit_replication":"https://pith.science/pith/MVB4AXDA6FL5CRPSUVP6S7RXAF/action/replication_record"}},"created_at":"2026-07-05T08:52:39.780787+00:00","updated_at":"2026-07-05T08:52:39.780787+00:00"}