{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O2BZVNK5AMDFONXQ66PYPONFQR","short_pith_number":"pith:O2BZVNK5","schema_version":"1.0","canonical_sha256":"76839ab55d03065736f0f79f87b9a5845e43392c94747e6a2b84c83e8b644cd7","source":{"kind":"arxiv","id":"2512.05337","version":2},"attestation_state":"computed","paper":{"title":"Symmetric Linear Dynamical Systems are Learnable from Few Observations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY","math.OC"],"primary_cat":"stat.ML","authors_text":"Andrey Y. Lokhov, Marc Vuffray, Minh Vu","submitted_at":"2025-12-05T00:33:31Z","abstract_excerpt":"We consider the problem of learning the parameters of a $N$-dimensional stochastic linear dynamics under both full and partial observations from a single trajectory of time $T$. We introduce and analyze a new estimator that achieves a small maximum element-wise error on the recovery of symmetric dynamic matrices using only $T=\\mathcal{O}(\\log N)$ observations, irrespective of whether the matrix is sparse or dense. This estimator is based on the method of moments and does not rely on problem-specific regularization. This is especially important for applications such as structure discovery."},"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":"2512.05337","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-12-05T00:33:31Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","math.OC"],"title_canon_sha256":"958956b17e86bb404951724597528d3453b509cec83500b4fdafde2454ed6ba3","abstract_canon_sha256":"acd563d3785be566ab90797f3fd095509f0db2e661f900cbc1b7091eb044be35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T00:18:11.967853Z","signature_b64":"nV6y1jSaUByohCKmRUHTozChIwzkw+xlu47iJpFsduqqKFMgY79N3+sVsmnnteT21xwz4YgVHPSFQeb9ujyxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76839ab55d03065736f0f79f87b9a5845e43392c94747e6a2b84c83e8b644cd7","last_reissued_at":"2026-06-25T00:18:11.967493Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T00:18:11.967493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symmetric Linear Dynamical Systems are Learnable from Few Observations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY","math.OC"],"primary_cat":"stat.ML","authors_text":"Andrey Y. Lokhov, Marc Vuffray, Minh Vu","submitted_at":"2025-12-05T00:33:31Z","abstract_excerpt":"We consider the problem of learning the parameters of a $N$-dimensional stochastic linear dynamics under both full and partial observations from a single trajectory of time $T$. We introduce and analyze a new estimator that achieves a small maximum element-wise error on the recovery of symmetric dynamic matrices using only $T=\\mathcal{O}(\\log N)$ observations, irrespective of whether the matrix is sparse or dense. This estimator is based on the method of moments and does not rely on problem-specific regularization. This is especially important for applications such as structure discovery."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.05337","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/2512.05337/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":"2512.05337","created_at":"2026-06-25T00:18:11.967554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.05337v2","created_at":"2026-06-25T00:18:11.967554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.05337","created_at":"2026-06-25T00:18:11.967554+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2BZVNK5AMDF","created_at":"2026-06-25T00:18:11.967554+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2BZVNK5AMDFONXQ","created_at":"2026-06-25T00:18:11.967554+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2BZVNK5","created_at":"2026-06-25T00:18:11.967554+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.05709","citing_title":"Network Reconstruction in Consensus Algorithms with Hidden Agents","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O2BZVNK5AMDFONXQ66PYPONFQR","json":"https://pith.science/pith/O2BZVNK5AMDFONXQ66PYPONFQR.json","graph_json":"https://pith.science/api/pith-number/O2BZVNK5AMDFONXQ66PYPONFQR/graph.json","events_json":"https://pith.science/api/pith-number/O2BZVNK5AMDFONXQ66PYPONFQR/events.json","paper":"https://pith.science/paper/O2BZVNK5"},"agent_actions":{"view_html":"https://pith.science/pith/O2BZVNK5AMDFONXQ66PYPONFQR","download_json":"https://pith.science/pith/O2BZVNK5AMDFONXQ66PYPONFQR.json","view_paper":"https://pith.science/paper/O2BZVNK5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.05337&json=true","fetch_graph":"https://pith.science/api/pith-number/O2BZVNK5AMDFONXQ66PYPONFQR/graph.json","fetch_events":"https://pith.science/api/pith-number/O2BZVNK5AMDFONXQ66PYPONFQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2BZVNK5AMDFONXQ66PYPONFQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2BZVNK5AMDFONXQ66PYPONFQR/action/storage_attestation","attest_author":"https://pith.science/pith/O2BZVNK5AMDFONXQ66PYPONFQR/action/author_attestation","sign_citation":"https://pith.science/pith/O2BZVNK5AMDFONXQ66PYPONFQR/action/citation_signature","submit_replication":"https://pith.science/pith/O2BZVNK5AMDFONXQ66PYPONFQR/action/replication_record"}},"created_at":"2026-06-25T00:18:11.967554+00:00","updated_at":"2026-06-25T00:18:11.967554+00:00"}