{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L7OVMBI4IVZVIGJTN35IUD6ZTZ","short_pith_number":"pith:L7OVMBI4","schema_version":"1.0","canonical_sha256":"5fdd56051c45735419336efa8a0fd99e5b01019c9ca2ae779f14ee14c2b16e9f","source":{"kind":"arxiv","id":"2604.21097","version":2},"attestation_state":"computed","paper":{"title":"Learning to Emulate Chaos: Adversarial Optimal Transport Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Adversarial optimal transport regularization trains neural emulators to match chaotic attractor statistics.","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Gabriel Melo, Leonardo Santiago, Peter Y. Lu","submitted_at":"2026-04-22T21:34:06Z","abstract_excerpt":"Chaos arises in many complex dynamical systems, from weather to power grids, but is difficult to accurately model with data-driven methods such as machine learning emulators. While emulators are promising tools for accelerating simulations and solving inverse problems, they still struggle to learn chaotic dynamics, where sensitivity to initial conditions renders exact long-term forecasts infeasible, especially given noisy data. Recent work instead trains emulators to match the statistical properties of chaotic attractors, but these approaches often rely on handcrafted summary statistics or lar"},"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":"2604.21097","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-04-22T21:34:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bfa6e7e595904e8222eaa7854be93274a8fcb0d0151f80effd5bab716e0ed62d","abstract_canon_sha256":"f8d9dbd14b83cf37dfa0ed9462d63ca069935c8c9eac081781553108ff8227e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:54.428889Z","signature_b64":"lshJiozHbEE5w1ZSoh4tSeRl5sH2lWBnUKU0mr1okGWtha4nUbMfWNTEqmgegT8jHMb1itNN66jl4LP3OMYUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fdd56051c45735419336efa8a0fd99e5b01019c9ca2ae779f14ee14c2b16e9f","last_reissued_at":"2026-06-19T16:12:54.428507Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:54.428507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Emulate Chaos: Adversarial Optimal Transport Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Adversarial optimal transport regularization trains neural emulators to match chaotic attractor statistics.","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Gabriel Melo, Leonardo Santiago, Peter Y. Lu","submitted_at":"2026-04-22T21:34:06Z","abstract_excerpt":"Chaos arises in many complex dynamical systems, from weather to power grids, but is difficult to accurately model with data-driven methods such as machine learning emulators. While emulators are promising tools for accelerating simulations and solving inverse problems, they still struggle to learn chaotic dynamics, where sensitivity to initial conditions renders exact long-term forecasts infeasible, especially given noisy data. Recent work instead trains emulators to match the statistical properties of chaotic attractors, but these approaches often rely on handcrafted summary statistics or lar"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our experiments across a variety of chaotic systems, including systems with high-dimensional chaotic attractors, show that emulators trained with our approach exhibit significantly improved long-term statistical fidelity.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That adversarial optimal transport regularization produces physically consistent emulators without introducing artifacts, instabilities, or distribution mismatches that affect downstream use.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Adversarial optimal transport objectives train neural emulators with improved long-term statistical fidelity on chaotic systems.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Adversarial optimal transport regularization trains neural emulators to match chaotic attractor statistics.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"00f6b239e574f7ea5008c08a52d6bd5f74b1edb212f7366e35b8d40285b267b5"},"source":{"id":"2604.21097","kind":"arxiv","version":2},"verdict":{"id":"6ff5e1d1-2aec-4bb8-9fd0-cbffb2d79666","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T22:45:48.433096Z","strongest_claim":"Our experiments across a variety of chaotic systems, including systems with high-dimensional chaotic attractors, show that emulators trained with our approach exhibit significantly improved long-term statistical fidelity.","one_line_summary":"Adversarial optimal transport objectives train neural emulators with improved long-term statistical fidelity on chaotic systems.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That adversarial optimal transport regularization produces physically consistent emulators without introducing artifacts, instabilities, or distribution mismatches that affect downstream use.","pith_extraction_headline":"Adversarial optimal transport regularization trains neural emulators to match chaotic attractor statistics."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.21097/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T13:37:43.739076Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T01:20:14.302944Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"c7a0aabe60e3c0f644117505bf44863600b279d7d2ec78d2e73c7d8323cec322"},"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":"2604.21097","created_at":"2026-06-19T16:12:54.428561+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.21097v2","created_at":"2026-06-19T16:12:54.428561+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.21097","created_at":"2026-06-19T16:12:54.428561+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7OVMBI4IVZV","created_at":"2026-06-19T16:12:54.428561+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7OVMBI4IVZVIGJT","created_at":"2026-06-19T16:12:54.428561+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7OVMBI4","created_at":"2026-06-19T16:12:54.428561+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.00391","citing_title":"Data-Adaptive Learning of Dynamical Systems by Matching Transfer Operators and Invariant Measures","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L7OVMBI4IVZVIGJTN35IUD6ZTZ","json":"https://pith.science/pith/L7OVMBI4IVZVIGJTN35IUD6ZTZ.json","graph_json":"https://pith.science/api/pith-number/L7OVMBI4IVZVIGJTN35IUD6ZTZ/graph.json","events_json":"https://pith.science/api/pith-number/L7OVMBI4IVZVIGJTN35IUD6ZTZ/events.json","paper":"https://pith.science/paper/L7OVMBI4"},"agent_actions":{"view_html":"https://pith.science/pith/L7OVMBI4IVZVIGJTN35IUD6ZTZ","download_json":"https://pith.science/pith/L7OVMBI4IVZVIGJTN35IUD6ZTZ.json","view_paper":"https://pith.science/paper/L7OVMBI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.21097&json=true","fetch_graph":"https://pith.science/api/pith-number/L7OVMBI4IVZVIGJTN35IUD6ZTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/L7OVMBI4IVZVIGJTN35IUD6ZTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7OVMBI4IVZVIGJTN35IUD6ZTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7OVMBI4IVZVIGJTN35IUD6ZTZ/action/storage_attestation","attest_author":"https://pith.science/pith/L7OVMBI4IVZVIGJTN35IUD6ZTZ/action/author_attestation","sign_citation":"https://pith.science/pith/L7OVMBI4IVZVIGJTN35IUD6ZTZ/action/citation_signature","submit_replication":"https://pith.science/pith/L7OVMBI4IVZVIGJTN35IUD6ZTZ/action/replication_record"}},"created_at":"2026-06-19T16:12:54.428561+00:00","updated_at":"2026-06-19T16:12:54.428561+00:00"}