{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H4PLUAGF2Y7UOVWO5YTLB23NHJ","short_pith_number":"pith:H4PLUAGF","schema_version":"1.0","canonical_sha256":"3f1eba00c5d63f4756ceee26b0eb6d3a4ece39d45967b628a6b8025849a466c0","source":{"kind":"arxiv","id":"2506.11639","version":1},"attestation_state":"computed","paper":{"title":"Recursive KalmanNet: Deep Learning-Augmented Kalman Filtering for State Estimation with Consistent Uncertainty Quantification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"eess.SP","authors_text":"Cyril Falcon, Hassan Mortada, Jean-Philippe Michel, Math\\'eo Clavaud, Yanis Kahil","submitted_at":"2025-06-13T10:11:32Z","abstract_excerpt":"State estimation in stochastic dynamical systems with noisy measurements is a challenge. While the Kalman filter is optimal for linear systems with independent Gaussian white noise, real-world conditions often deviate from these assumptions, prompting the rise of data-driven filtering techniques. This paper introduces Recursive KalmanNet, a Kalman-filter-informed recurrent neural network designed for accurate state estimation with consistent error covariance quantification. Our approach propagates error covariance using the recursive Joseph's formula and optimizes the Gaussian negative log-lik"},"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":"2506.11639","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SP","submitted_at":"2025-06-13T10:11:32Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"c81d534565485e50dc036baae37aa29713dcf4f6797e6e49556b5d31f26dc13e","abstract_canon_sha256":"7d41392fb84e5cf391a462a7640c78759196d3e7a23a2202b680405f95be877e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:20.740250Z","signature_b64":"MQ/IBQdhDr37fBWmc7PVbZRzmV+TzVpTH2/ALY3RAgz6wNnrfk43T4nXt+0gYzR8NUhuw05bJzR/l6LK7OPnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f1eba00c5d63f4756ceee26b0eb6d3a4ece39d45967b628a6b8025849a466c0","last_reissued_at":"2026-07-05T12:09:20.739716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:20.739716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recursive KalmanNet: Deep Learning-Augmented Kalman Filtering for State Estimation with Consistent Uncertainty Quantification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"eess.SP","authors_text":"Cyril Falcon, Hassan Mortada, Jean-Philippe Michel, Math\\'eo Clavaud, Yanis Kahil","submitted_at":"2025-06-13T10:11:32Z","abstract_excerpt":"State estimation in stochastic dynamical systems with noisy measurements is a challenge. While the Kalman filter is optimal for linear systems with independent Gaussian white noise, real-world conditions often deviate from these assumptions, prompting the rise of data-driven filtering techniques. This paper introduces Recursive KalmanNet, a Kalman-filter-informed recurrent neural network designed for accurate state estimation with consistent error covariance quantification. Our approach propagates error covariance using the recursive Joseph's formula and optimizes the Gaussian negative log-lik"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11639","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/2506.11639/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":"2506.11639","created_at":"2026-07-05T12:09:20.739775+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11639v1","created_at":"2026-07-05T12:09:20.739775+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11639","created_at":"2026-07-05T12:09:20.739775+00:00"},{"alias_kind":"pith_short_12","alias_value":"H4PLUAGF2Y7U","created_at":"2026-07-05T12:09:20.739775+00:00"},{"alias_kind":"pith_short_16","alias_value":"H4PLUAGF2Y7UOVWO","created_at":"2026-07-05T12:09:20.739775+00:00"},{"alias_kind":"pith_short_8","alias_value":"H4PLUAGF","created_at":"2026-07-05T12:09:20.739775+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02767","citing_title":"Hybrid Adaptive Kalman Filtering for Data-Efficient Joint Tracking and Classification","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02251","citing_title":"FW-NKF: Frequency-Weighted Neural Kalman Filters","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H4PLUAGF2Y7UOVWO5YTLB23NHJ","json":"https://pith.science/pith/H4PLUAGF2Y7UOVWO5YTLB23NHJ.json","graph_json":"https://pith.science/api/pith-number/H4PLUAGF2Y7UOVWO5YTLB23NHJ/graph.json","events_json":"https://pith.science/api/pith-number/H4PLUAGF2Y7UOVWO5YTLB23NHJ/events.json","paper":"https://pith.science/paper/H4PLUAGF"},"agent_actions":{"view_html":"https://pith.science/pith/H4PLUAGF2Y7UOVWO5YTLB23NHJ","download_json":"https://pith.science/pith/H4PLUAGF2Y7UOVWO5YTLB23NHJ.json","view_paper":"https://pith.science/paper/H4PLUAGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11639&json=true","fetch_graph":"https://pith.science/api/pith-number/H4PLUAGF2Y7UOVWO5YTLB23NHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/H4PLUAGF2Y7UOVWO5YTLB23NHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H4PLUAGF2Y7UOVWO5YTLB23NHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H4PLUAGF2Y7UOVWO5YTLB23NHJ/action/storage_attestation","attest_author":"https://pith.science/pith/H4PLUAGF2Y7UOVWO5YTLB23NHJ/action/author_attestation","sign_citation":"https://pith.science/pith/H4PLUAGF2Y7UOVWO5YTLB23NHJ/action/citation_signature","submit_replication":"https://pith.science/pith/H4PLUAGF2Y7UOVWO5YTLB23NHJ/action/replication_record"}},"created_at":"2026-07-05T12:09:20.739775+00:00","updated_at":"2026-07-05T12:09:20.739775+00:00"}