{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:S7ED74E5K2DDUF2MGHPCNDFQ2Y","short_pith_number":"pith:S7ED74E5","schema_version":"1.0","canonical_sha256":"97c83ff09d56863a174c31de268cb0d601ebf34bed93688d6906a96c79ebabcb","source":{"kind":"arxiv","id":"2111.08626","version":2},"attestation_state":"computed","paper":{"title":"Adjoint-Matching Neural Network Surrogates for Fast 4D-Var Data Assimilation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE","cs.NA","math.NA","math.OC"],"primary_cat":"cs.LG","authors_text":"Adrian Sandu, Ali Haisam Muhammad Rafid, Amit N. Subrahmanya, Andrey A. Popov, Anuj Karpatne, Austin Chennault, Rachel Cooper","submitted_at":"2021-11-16T17:11:05Z","abstract_excerpt":"Data assimilation is the process of fusing information from imperfect computer simulations with noisy, sparse measurements of reality to obtain improved estimates of the state or parameters of a dynamical system of interest. The data assimilation procedures used in many geoscience applications, such as numerical weather forecasting, are variants of the our-dimensional variational (4D-Var) algorithm. The cost of solving the underlying 4D-Var optimization problem is dominated by the cost of repeated forward and adjoint model runs. This motivates substituting the evaluations of the physical model"},"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":"2111.08626","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-16T17:11:05Z","cross_cats_sorted":["cs.CE","cs.NA","math.NA","math.OC"],"title_canon_sha256":"5297725139245f167531ffab093adf906aa6e3d9912c11bc2df00b8535f07f39","abstract_canon_sha256":"80b7587996368ba85424fc3a2700aed831a9dd8bb9034903a9d2b7a34f260358"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:09.075978Z","signature_b64":"mI2ou3mLAyi91KU3LlA8bZG+djn+gWHxGVMiO9L9U4J2nxjCTykEG3uv1hQ+QXIblGnWtTfXa444EoVu1/sUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97c83ff09d56863a174c31de268cb0d601ebf34bed93688d6906a96c79ebabcb","last_reissued_at":"2026-07-05T05:27:09.075510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:09.075510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adjoint-Matching Neural Network Surrogates for Fast 4D-Var Data Assimilation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE","cs.NA","math.NA","math.OC"],"primary_cat":"cs.LG","authors_text":"Adrian Sandu, Ali Haisam Muhammad Rafid, Amit N. Subrahmanya, Andrey A. Popov, Anuj Karpatne, Austin Chennault, Rachel Cooper","submitted_at":"2021-11-16T17:11:05Z","abstract_excerpt":"Data assimilation is the process of fusing information from imperfect computer simulations with noisy, sparse measurements of reality to obtain improved estimates of the state or parameters of a dynamical system of interest. The data assimilation procedures used in many geoscience applications, such as numerical weather forecasting, are variants of the our-dimensional variational (4D-Var) algorithm. The cost of solving the underlying 4D-Var optimization problem is dominated by the cost of repeated forward and adjoint model runs. This motivates substituting the evaluations of the physical model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08626","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/2111.08626/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":"2111.08626","created_at":"2026-07-05T05:27:09.075577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.08626v2","created_at":"2026-07-05T05:27:09.075577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08626","created_at":"2026-07-05T05:27:09.075577+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7ED74E5K2DD","created_at":"2026-07-05T05:27:09.075577+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7ED74E5K2DDUF2M","created_at":"2026-07-05T05:27:09.075577+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7ED74E5","created_at":"2026-07-05T05:27:09.075577+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.09009","citing_title":"A physics-informed transformer neural operator for learning generalized solutions of initial boundary value problems","ref_index":62,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S7ED74E5K2DDUF2MGHPCNDFQ2Y","json":"https://pith.science/pith/S7ED74E5K2DDUF2MGHPCNDFQ2Y.json","graph_json":"https://pith.science/api/pith-number/S7ED74E5K2DDUF2MGHPCNDFQ2Y/graph.json","events_json":"https://pith.science/api/pith-number/S7ED74E5K2DDUF2MGHPCNDFQ2Y/events.json","paper":"https://pith.science/paper/S7ED74E5"},"agent_actions":{"view_html":"https://pith.science/pith/S7ED74E5K2DDUF2MGHPCNDFQ2Y","download_json":"https://pith.science/pith/S7ED74E5K2DDUF2MGHPCNDFQ2Y.json","view_paper":"https://pith.science/paper/S7ED74E5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.08626&json=true","fetch_graph":"https://pith.science/api/pith-number/S7ED74E5K2DDUF2MGHPCNDFQ2Y/graph.json","fetch_events":"https://pith.science/api/pith-number/S7ED74E5K2DDUF2MGHPCNDFQ2Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7ED74E5K2DDUF2MGHPCNDFQ2Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7ED74E5K2DDUF2MGHPCNDFQ2Y/action/storage_attestation","attest_author":"https://pith.science/pith/S7ED74E5K2DDUF2MGHPCNDFQ2Y/action/author_attestation","sign_citation":"https://pith.science/pith/S7ED74E5K2DDUF2MGHPCNDFQ2Y/action/citation_signature","submit_replication":"https://pith.science/pith/S7ED74E5K2DDUF2MGHPCNDFQ2Y/action/replication_record"}},"created_at":"2026-07-05T05:27:09.075577+00:00","updated_at":"2026-07-05T05:27:09.075577+00:00"}