{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MKL75JF5NRDYZ2I2YGSBYB4OYB","short_pith_number":"pith:MKL75JF5","schema_version":"1.0","canonical_sha256":"6297fea4bd6c478ce91ac1a41c078ec07c461da3ff81b1bd5391facb4110b4d2","source":{"kind":"arxiv","id":"2504.02995","version":1},"attestation_state":"computed","paper":{"title":"Online Learning for Nonlinear Dynamical Systems without the I.I.D. Condition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Lantian Zhang, Silun Zhang","submitted_at":"2025-04-03T19:35:38Z","abstract_excerpt":"This paper investigates online identification and prediction for nonlinear stochastic dynamical systems. In contrast to offline learning methods, we develop online algorithms that learn unknown parameters from a single trajectory. A key challenge in this setting is handling the non-independent data generated by the closed-loop system. Existing theoretical guarantees for such systems are mostly restricted to the assumption that inputs are independently and identically distributed (i.i.d.), or that the closed-loop data satisfy a persistent excitation (PE) condition. However, these assumptions ar"},"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":"2504.02995","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2025-04-03T19:35:38Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"252c382434e7ec6c01b67086b33fa394b2856447f9841c29671bbdf16bc17536","abstract_canon_sha256":"c40d29b8915a92db41409d28e15f41a2eda6c87066f6e6b8a6fc31c01eaeca4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:24.210295Z","signature_b64":"CLfR9gLvRqg3SzeGzLZz/GfeDU3e/2P2g3HLv/qpztL4I4Wh78jPA8RY37F3vY/Vlzj4qFeXjFlth4hKOdLPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6297fea4bd6c478ce91ac1a41c078ec07c461da3ff81b1bd5391facb4110b4d2","last_reissued_at":"2026-07-05T10:44:24.209845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:24.209845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Learning for Nonlinear Dynamical Systems without the I.I.D. Condition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Lantian Zhang, Silun Zhang","submitted_at":"2025-04-03T19:35:38Z","abstract_excerpt":"This paper investigates online identification and prediction for nonlinear stochastic dynamical systems. In contrast to offline learning methods, we develop online algorithms that learn unknown parameters from a single trajectory. A key challenge in this setting is handling the non-independent data generated by the closed-loop system. Existing theoretical guarantees for such systems are mostly restricted to the assumption that inputs are independently and identically distributed (i.i.d.), or that the closed-loop data satisfy a persistent excitation (PE) condition. However, these assumptions ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02995","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/2504.02995/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":"2504.02995","created_at":"2026-07-05T10:44:24.209899+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02995v1","created_at":"2026-07-05T10:44:24.209899+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02995","created_at":"2026-07-05T10:44:24.209899+00:00"},{"alias_kind":"pith_short_12","alias_value":"MKL75JF5NRDY","created_at":"2026-07-05T10:44:24.209899+00:00"},{"alias_kind":"pith_short_16","alias_value":"MKL75JF5NRDYZ2I2","created_at":"2026-07-05T10:44:24.209899+00:00"},{"alias_kind":"pith_short_8","alias_value":"MKL75JF5","created_at":"2026-07-05T10:44:24.209899+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02529","citing_title":"A No-Regret Framework for Adaptive Incentive Design","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06980","citing_title":"Stochastic Adaptive Control for Systems with Nonlinear Parameterization: Almost Sure Stability and Tracking","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MKL75JF5NRDYZ2I2YGSBYB4OYB","json":"https://pith.science/pith/MKL75JF5NRDYZ2I2YGSBYB4OYB.json","graph_json":"https://pith.science/api/pith-number/MKL75JF5NRDYZ2I2YGSBYB4OYB/graph.json","events_json":"https://pith.science/api/pith-number/MKL75JF5NRDYZ2I2YGSBYB4OYB/events.json","paper":"https://pith.science/paper/MKL75JF5"},"agent_actions":{"view_html":"https://pith.science/pith/MKL75JF5NRDYZ2I2YGSBYB4OYB","download_json":"https://pith.science/pith/MKL75JF5NRDYZ2I2YGSBYB4OYB.json","view_paper":"https://pith.science/paper/MKL75JF5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02995&json=true","fetch_graph":"https://pith.science/api/pith-number/MKL75JF5NRDYZ2I2YGSBYB4OYB/graph.json","fetch_events":"https://pith.science/api/pith-number/MKL75JF5NRDYZ2I2YGSBYB4OYB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MKL75JF5NRDYZ2I2YGSBYB4OYB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MKL75JF5NRDYZ2I2YGSBYB4OYB/action/storage_attestation","attest_author":"https://pith.science/pith/MKL75JF5NRDYZ2I2YGSBYB4OYB/action/author_attestation","sign_citation":"https://pith.science/pith/MKL75JF5NRDYZ2I2YGSBYB4OYB/action/citation_signature","submit_replication":"https://pith.science/pith/MKL75JF5NRDYZ2I2YGSBYB4OYB/action/replication_record"}},"created_at":"2026-07-05T10:44:24.209899+00:00","updated_at":"2026-07-05T10:44:24.209899+00:00"}