{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DS5AWKBEBN23AM6VVWLCCZG23D","short_pith_number":"pith:DS5AWKBE","schema_version":"1.0","canonical_sha256":"1cba0b28240b75b033d5ad962164dad8df835fef432b87ec78638db6f0e43c4f","source":{"kind":"arxiv","id":"1806.05722","version":2},"attestation_state":"computed","paper":{"title":"Non-asymptotic Identification of LTI Systems from a Single Trajectory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Necmiye Ozay, Samet Oymak","submitted_at":"2018-06-14T20:05:25Z","abstract_excerpt":"We consider the problem of learning a realization for a linear time-invariant (LTI) dynamical system from input/output data. Given a single input/output trajectory, we provide finite time analysis for learning the system's Markov parameters, from which a balanced realization is obtained using the classical Ho-Kalman algorithm. By proving a stability result for the Ho-Kalman algorithm and combining it with the sample complexity results for Markov parameters, we show how much data is needed to learn a balanced realization of the system up to a desired accuracy with high probability."},"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":"1806.05722","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-14T20:05:25Z","cross_cats_sorted":["cs.SY","math.OC","stat.ML"],"title_canon_sha256":"c4d05dd782702e55e52ba4104d3bb8a0857189da289316559af459d0f6848467","abstract_canon_sha256":"294f97fa307d43f0c1efbec8a288c17225e9e08f2a5e4cd04128d225eaec2c61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:54.207484Z","signature_b64":"cm7+FYvbdvDDGkClGJ2SXU6hLVPRcVq3PSBl1X2dwhOm8/rZhscOH6nJdl7W/8+bzpjfY8Cd9gkDXqjwvkMbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cba0b28240b75b033d5ad962164dad8df835fef432b87ec78638db6f0e43c4f","last_reissued_at":"2026-05-17T23:54:54.206947Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:54.206947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-asymptotic Identification of LTI Systems from a Single Trajectory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Necmiye Ozay, Samet Oymak","submitted_at":"2018-06-14T20:05:25Z","abstract_excerpt":"We consider the problem of learning a realization for a linear time-invariant (LTI) dynamical system from input/output data. Given a single input/output trajectory, we provide finite time analysis for learning the system's Markov parameters, from which a balanced realization is obtained using the classical Ho-Kalman algorithm. By proving a stability result for the Ho-Kalman algorithm and combining it with the sample complexity results for Markov parameters, we show how much data is needed to learn a balanced realization of the system up to a desired accuracy with high probability."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05722","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":""},"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":"1806.05722","created_at":"2026-05-17T23:54:54.207017+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.05722v2","created_at":"2026-05-17T23:54:54.207017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05722","created_at":"2026-05-17T23:54:54.207017+00:00"},{"alias_kind":"pith_short_12","alias_value":"DS5AWKBEBN23","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DS5AWKBEBN23AM6V","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DS5AWKBE","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17213","citing_title":"Symplectic Inductive Bias for Data-Driven Target Reachability in Hamiltonian Systems","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DS5AWKBEBN23AM6VVWLCCZG23D","json":"https://pith.science/pith/DS5AWKBEBN23AM6VVWLCCZG23D.json","graph_json":"https://pith.science/api/pith-number/DS5AWKBEBN23AM6VVWLCCZG23D/graph.json","events_json":"https://pith.science/api/pith-number/DS5AWKBEBN23AM6VVWLCCZG23D/events.json","paper":"https://pith.science/paper/DS5AWKBE"},"agent_actions":{"view_html":"https://pith.science/pith/DS5AWKBEBN23AM6VVWLCCZG23D","download_json":"https://pith.science/pith/DS5AWKBEBN23AM6VVWLCCZG23D.json","view_paper":"https://pith.science/paper/DS5AWKBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.05722&json=true","fetch_graph":"https://pith.science/api/pith-number/DS5AWKBEBN23AM6VVWLCCZG23D/graph.json","fetch_events":"https://pith.science/api/pith-number/DS5AWKBEBN23AM6VVWLCCZG23D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DS5AWKBEBN23AM6VVWLCCZG23D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DS5AWKBEBN23AM6VVWLCCZG23D/action/storage_attestation","attest_author":"https://pith.science/pith/DS5AWKBEBN23AM6VVWLCCZG23D/action/author_attestation","sign_citation":"https://pith.science/pith/DS5AWKBEBN23AM6VVWLCCZG23D/action/citation_signature","submit_replication":"https://pith.science/pith/DS5AWKBEBN23AM6VVWLCCZG23D/action/replication_record"}},"created_at":"2026-05-17T23:54:54.207017+00:00","updated_at":"2026-05-17T23:54:54.207017+00:00"}