{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GAXT4SWNPONHRYUY2IOGT5MWGF","short_pith_number":"pith:GAXT4SWN","schema_version":"1.0","canonical_sha256":"302f3e4acd7b9a78e298d21c69f596314a8e1ac459d54a7ed2ede1e6387fe6c4","source":{"kind":"arxiv","id":"2507.09652","version":1},"attestation_state":"computed","paper":{"title":"Machine-Precision Prediction of Low-Dimensional Chaotic Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.DS"],"primary_cat":"nlin.CD","authors_text":"Christof Sch\\\"otz, Niklas Boers","submitted_at":"2025-07-13T14:36:47Z","abstract_excerpt":"Low-dimensional chaotic systems such as the Lorenz-63 model are commonly used to benchmark system-agnostic methods for learning dynamics from data. Here we show that learning from noise-free observations in such systems can be achieved up to machine precision: using ordinary least squares regression on high-degree polynomial features with 512-bit arithmetic, our method exceeds the accuracy of standard 64-bit numerical ODE solvers of the true underlying dynamical systems. Depending on the configuration, we obtain valid prediction times of 32 to 105 Lyapunov times for the Lorenz-63 system, drama"},"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":"2507.09652","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"nlin.CD","submitted_at":"2025-07-13T14:36:47Z","cross_cats_sorted":["cs.LG","math.DS"],"title_canon_sha256":"766ae7a224db0c0cba371f449c67bd8966f05ca42ef99aad81b97eadd3be43f6","abstract_canon_sha256":"662b14f4024e2f0264b3975e0fc67997649c6e13c4fda3fa5cdd1da4d2d7ea46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:37.417840Z","signature_b64":"3UPR6LL2/Zu+mG7FeI+3ea0f+P8OGco/uBjdZon0xXvlGY1sxk83VnpyjAAoh4W5IDMI+iTWm70UQIWrE34rDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"302f3e4acd7b9a78e298d21c69f596314a8e1ac459d54a7ed2ede1e6387fe6c4","last_reissued_at":"2026-07-05T11:36:37.417375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:37.417375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine-Precision Prediction of Low-Dimensional Chaotic Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.DS"],"primary_cat":"nlin.CD","authors_text":"Christof Sch\\\"otz, Niklas Boers","submitted_at":"2025-07-13T14:36:47Z","abstract_excerpt":"Low-dimensional chaotic systems such as the Lorenz-63 model are commonly used to benchmark system-agnostic methods for learning dynamics from data. Here we show that learning from noise-free observations in such systems can be achieved up to machine precision: using ordinary least squares regression on high-degree polynomial features with 512-bit arithmetic, our method exceeds the accuracy of standard 64-bit numerical ODE solvers of the true underlying dynamical systems. Depending on the configuration, we obtain valid prediction times of 32 to 105 Lyapunov times for the Lorenz-63 system, drama"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09652","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/2507.09652/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":"2507.09652","created_at":"2026-07-05T11:36:37.417433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09652v1","created_at":"2026-07-05T11:36:37.417433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09652","created_at":"2026-07-05T11:36:37.417433+00:00"},{"alias_kind":"pith_short_12","alias_value":"GAXT4SWNPONH","created_at":"2026-07-05T11:36:37.417433+00:00"},{"alias_kind":"pith_short_16","alias_value":"GAXT4SWNPONHRYUY","created_at":"2026-07-05T11:36:37.417433+00:00"},{"alias_kind":"pith_short_8","alias_value":"GAXT4SWN","created_at":"2026-07-05T11:36:37.417433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.31438","citing_title":"Flow map learning in nonlinear vector autoregressive models: influence of the feature-library structure on the training error","ref_index":109,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GAXT4SWNPONHRYUY2IOGT5MWGF","json":"https://pith.science/pith/GAXT4SWNPONHRYUY2IOGT5MWGF.json","graph_json":"https://pith.science/api/pith-number/GAXT4SWNPONHRYUY2IOGT5MWGF/graph.json","events_json":"https://pith.science/api/pith-number/GAXT4SWNPONHRYUY2IOGT5MWGF/events.json","paper":"https://pith.science/paper/GAXT4SWN"},"agent_actions":{"view_html":"https://pith.science/pith/GAXT4SWNPONHRYUY2IOGT5MWGF","download_json":"https://pith.science/pith/GAXT4SWNPONHRYUY2IOGT5MWGF.json","view_paper":"https://pith.science/paper/GAXT4SWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09652&json=true","fetch_graph":"https://pith.science/api/pith-number/GAXT4SWNPONHRYUY2IOGT5MWGF/graph.json","fetch_events":"https://pith.science/api/pith-number/GAXT4SWNPONHRYUY2IOGT5MWGF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GAXT4SWNPONHRYUY2IOGT5MWGF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GAXT4SWNPONHRYUY2IOGT5MWGF/action/storage_attestation","attest_author":"https://pith.science/pith/GAXT4SWNPONHRYUY2IOGT5MWGF/action/author_attestation","sign_citation":"https://pith.science/pith/GAXT4SWNPONHRYUY2IOGT5MWGF/action/citation_signature","submit_replication":"https://pith.science/pith/GAXT4SWNPONHRYUY2IOGT5MWGF/action/replication_record"}},"created_at":"2026-07-05T11:36:37.417433+00:00","updated_at":"2026-07-05T11:36:37.417433+00:00"}