{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KA3KABDAVKQEFFT2DLIZGHFGVL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6401616309b088f5aa8531264caaa7bdd987e42be4f6f6c94d48002809ce4f69","cross_cats_sorted":["math.DS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T05:45:41Z","title_canon_sha256":"2b76a4e81213cddf5c295141dbb4b280394cadae6bc89c4b3eb09587e2e73723"},"schema_version":"1.0","source":{"id":"2605.14405","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14405","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14405v1","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14405","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"KA3KABDAVKQE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KA3KABDAVKQEFFT2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KA3KABDA","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:fcfce1ded193873be68dbe5f2f1d5612ce746c0a20e41e6c6be253d9b77bef58","target":"graph","created_at":"2026-05-17T23:39:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our method constructs a local covering of a chaotic attractor in phase space and analyzes the expansion and contraction of these coverings under the dynamics. The surrogate model is trained by minimizing the maximum mean discrepancy between the pushforward distributions of the coverings under the surrogate and ground-truth dynamics. Experiments show that our method significantly improves Jacobian accuracy while remaining competitive with state-of-the-art statistically accurate dynamics learning methods."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the chosen local coverings are sufficiently representative of the attractor and that minimizing MMD on their pushforwards will simultaneously enforce accurate Jacobians without introducing new biases in the learned dynamics."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"The framework trains chaotic surrogates by minimizing MMD between pushforward distributions of local phase-space coverings under the model and ground truth, yielding improved Jacobian accuracy while staying competitive on statistical fidelity."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A surrogate model for chaotic dynamics is trained by matching pushforward distributions of local phase space coverings under maximum mean discrepancy to achieve both accurate Jacobians and long-term statistics."}],"snapshot_sha256":"e0dd5952b03cffa61035a7c142404d71f0737e89fd642c100a57142d25e74934"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3de38ca8478a1d8701add0037413ca7c39c4fa7a6d5595a2f22ca29d10fcc423"},"paper":{"abstract_excerpt":"Chaotic systems pose fundamental challenges for data-driven dynamics discovery, as small modeling errors lead to exponentially growing trajectory discrepancies. Since exact long-term prediction is unattainable, it is natural to ask what a good surrogate model for chaotic dynamics is. Prior work has largely focused either on reproducing the Jacobian of the underlying dynamics, which governs local expansion and contraction rates, or on training surrogate models that reproduce the ground-truth dynamics' long-term statistical behavior. In this work, we propose a new framework that aims to bridge t","authors_text":"Andrus Giraldo, Deok-Sun Lee, Joon-Hyuk Ko","cross_cats":["math.DS"],"headline":"A surrogate model for chaotic dynamics is trained by matching pushforward distributions of local phase space coverings under maximum mean discrepancy to achieve both accurate Jacobians and long-term statistics.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T05:45:41Z","title":"Watch your neighbors: Training statistically accurate chaotic systems with local phase space information"},"references":{"count":62,"internal_anchors":0,"resolved_work":62,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"H. D. I. Abarbanel, R. Brown, and M. B. Kennel. Variation of Lyapunov exponents on a strange attractor.J Nonlinear Sci, 1(2):175–199, 1991","work_id":"498154a9-095f-4c4f-827c-b193422b6469","year":1991},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"H. D. I. Abarbanel, R. Brown, and M. B. Kennel. Local Lyapunov exponents computed from observed data.J Nonlinear Sci, 2(3):343–365, 1992","work_id":"7293f164-6352-49c6-adcf-75ac7ecc63e3","year":1992},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"K. T. Alligood, T. Sauer, and J. A. Yorke.Chaos: An Introduction to Dynamical Systems, chapter 2.1 Mathematical Models. Textbooks in Mathematical Sciences. Springer, New York, 1996","work_id":"10f9c908-cf06-4f27-a551-38ea47295380","year":1996},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"M. Ataei, A. Khaki-Sedigh, B. Lohmann, and C. Lucas. Estimating the Lyapunov exponents of chaotic time series: A model based method. In2003 European Control Conference (ECC), pages 3106–3111, 2003","work_id":"fec6b1d5-4841-452b-8a84-72e3c80cbb8d","year":2003},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"D. Ayers, J. Lau, J. Amezcua, A. Carrassi, and V . Ojha. Supervised machine learning to estimate instabilities in chaotic systems: Estimation of local Lyapunov exponents.Quarterly Journal of the Royal","work_id":"611cf97c-740f-49ba-b2c6-e143c225bde6","year":2023}],"snapshot_sha256":"a16533777a901175c3a1776aa38a495549f05b4acc2d9a3bcd9d07937097b892"},"source":{"id":"2605.14405","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:32:07.066136Z","id":"43fb6b5f-d733-4617-8864-975642dec057","model_set":{"reader":"grok-4.3"},"one_line_summary":"The framework trains chaotic surrogates by minimizing MMD between pushforward distributions of local phase-space coverings under the model and ground truth, yielding improved Jacobian accuracy while staying competitive on statistical fidelity.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A surrogate model for chaotic dynamics is trained by matching pushforward distributions of local phase space coverings under maximum mean discrepancy to achieve both accurate Jacobians and long-term statistics.","strongest_claim":"Our method constructs a local covering of a chaotic attractor in phase space and analyzes the expansion and contraction of these coverings under the dynamics. The surrogate model is trained by minimizing the maximum mean discrepancy between the pushforward distributions of the coverings under the surrogate and ground-truth dynamics. Experiments show that our method significantly improves Jacobian accuracy while remaining competitive with state-of-the-art statistically accurate dynamics learning methods.","weakest_assumption":"That the chosen local coverings are sufficiently representative of the attractor and that minimizing MMD on their pushforwards will simultaneously enforce accurate Jacobians without introducing new biases in the learned dynamics."}},"verdict_id":"43fb6b5f-d733-4617-8864-975642dec057"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e5434ebaa58e3a1f5d1b55e03871e931f1ad20e5129725b705e9a73056326b64","target":"record","created_at":"2026-05-17T23:39:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6401616309b088f5aa8531264caaa7bdd987e42be4f6f6c94d48002809ce4f69","cross_cats_sorted":["math.DS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T05:45:41Z","title_canon_sha256":"2b76a4e81213cddf5c295141dbb4b280394cadae6bc89c4b3eb09587e2e73723"},"schema_version":"1.0","source":{"id":"2605.14405","kind":"arxiv","version":1}},"canonical_sha256":"5036a00460aaa042967a1ad1931ca6aaf1caccebd4e6c117cb64cf05f90fd599","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5036a00460aaa042967a1ad1931ca6aaf1caccebd4e6c117cb64cf05f90fd599","first_computed_at":"2026-05-17T23:39:07.435703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:07.435703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QyFO7/oN73lChlheU7GdT0CVsncIBjc9XvSkPdGcElN+R/0E0mHAWQz1MmYTjvk+2HqylzmrJlUAl64IA0JHDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:07.436388Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14405","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5434ebaa58e3a1f5d1b55e03871e931f1ad20e5129725b705e9a73056326b64","sha256:fcfce1ded193873be68dbe5f2f1d5612ce746c0a20e41e6c6be253d9b77bef58"],"state_sha256":"504015a2008571d709a54a443ca05fba81bc772c7e5908b153317d7c206536c5"}