{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:C2UM7DDB7WLVVJ3K3CF3K3S5VC","short_pith_number":"pith:C2UM7DDB","schema_version":"1.0","canonical_sha256":"16a8cf8c61fd975aa76ad88bb56e5da8952d275b1dc877797e63f2be210b9e46","source":{"kind":"arxiv","id":"2110.09005","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Learned Kalman Filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.SP","authors_text":"Guy Revach, Nir Shlezinger, Ruud J. G. van Sloun, Timur Locher, Xiaoyong Ni, Yonina C. Eldar","submitted_at":"2021-10-18T04:04:09Z","abstract_excerpt":"In this paper we adapt KalmanNet, which is a recently pro-posed deep neural network (DNN)-aided system whose architecture follows the operation of the model-based Kalman filter (KF), to learn its mapping in an unsupervised manner, i.e., without requiring ground-truth states. The unsupervised adaptation is achieved by exploiting the hybrid model-based/data-driven architecture of KalmanNet, which internally predicts the next observation as the KF does. These internal features are then used to compute the loss rather than the state estimate at the output of the system. With the capability of unsu"},"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":"2110.09005","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SP","submitted_at":"2021-10-18T04:04:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5fad92798f3acfc3b1abed9aae1299deb99d0a696c145794e4e6d47e5ecc0194","abstract_canon_sha256":"cd7d67d8e9a8282fc52373f3a3db0feb60a97fbc18a0091689659645fed94992"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:22.892833Z","signature_b64":"pWbUL9AIpyQQr0DPNMzQvs97sYKJDqQlxkvHJAoTTWx3yv2XERit2xGothcmTAJWDYX1VpV1PcofJWPtBX4cCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16a8cf8c61fd975aa76ad88bb56e5da8952d275b1dc877797e63f2be210b9e46","last_reissued_at":"2026-07-05T03:23:22.892356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:22.892356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Learned Kalman Filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.SP","authors_text":"Guy Revach, Nir Shlezinger, Ruud J. G. van Sloun, Timur Locher, Xiaoyong Ni, Yonina C. Eldar","submitted_at":"2021-10-18T04:04:09Z","abstract_excerpt":"In this paper we adapt KalmanNet, which is a recently pro-posed deep neural network (DNN)-aided system whose architecture follows the operation of the model-based Kalman filter (KF), to learn its mapping in an unsupervised manner, i.e., without requiring ground-truth states. The unsupervised adaptation is achieved by exploiting the hybrid model-based/data-driven architecture of KalmanNet, which internally predicts the next observation as the KF does. These internal features are then used to compute the loss rather than the state estimate at the output of the system. With the capability of unsu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09005","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/2110.09005/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":"2110.09005","created_at":"2026-07-05T03:23:22.892413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.09005v1","created_at":"2026-07-05T03:23:22.892413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09005","created_at":"2026-07-05T03:23:22.892413+00:00"},{"alias_kind":"pith_short_12","alias_value":"C2UM7DDB7WLV","created_at":"2026-07-05T03:23:22.892413+00:00"},{"alias_kind":"pith_short_16","alias_value":"C2UM7DDB7WLVVJ3K","created_at":"2026-07-05T03:23:22.892413+00:00"},{"alias_kind":"pith_short_8","alias_value":"C2UM7DDB","created_at":"2026-07-05T03:23:22.892413+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26286","citing_title":"Decoupled Delay Compensation: Enhancing Pre-trained MARL Policies via Learned Dynamics Filtering","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C2UM7DDB7WLVVJ3K3CF3K3S5VC","json":"https://pith.science/pith/C2UM7DDB7WLVVJ3K3CF3K3S5VC.json","graph_json":"https://pith.science/api/pith-number/C2UM7DDB7WLVVJ3K3CF3K3S5VC/graph.json","events_json":"https://pith.science/api/pith-number/C2UM7DDB7WLVVJ3K3CF3K3S5VC/events.json","paper":"https://pith.science/paper/C2UM7DDB"},"agent_actions":{"view_html":"https://pith.science/pith/C2UM7DDB7WLVVJ3K3CF3K3S5VC","download_json":"https://pith.science/pith/C2UM7DDB7WLVVJ3K3CF3K3S5VC.json","view_paper":"https://pith.science/paper/C2UM7DDB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.09005&json=true","fetch_graph":"https://pith.science/api/pith-number/C2UM7DDB7WLVVJ3K3CF3K3S5VC/graph.json","fetch_events":"https://pith.science/api/pith-number/C2UM7DDB7WLVVJ3K3CF3K3S5VC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C2UM7DDB7WLVVJ3K3CF3K3S5VC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C2UM7DDB7WLVVJ3K3CF3K3S5VC/action/storage_attestation","attest_author":"https://pith.science/pith/C2UM7DDB7WLVVJ3K3CF3K3S5VC/action/author_attestation","sign_citation":"https://pith.science/pith/C2UM7DDB7WLVVJ3K3CF3K3S5VC/action/citation_signature","submit_replication":"https://pith.science/pith/C2UM7DDB7WLVVJ3K3CF3K3S5VC/action/replication_record"}},"created_at":"2026-07-05T03:23:22.892413+00:00","updated_at":"2026-07-05T03:23:22.892413+00:00"}