{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UQZJKP6HNTWEC42FKFIFBDXAGG","short_pith_number":"pith:UQZJKP6H","schema_version":"1.0","canonical_sha256":"a432953fc76cec4173455150508ee031ad587205382675bcb3794a32e3b6a249","source":{"kind":"arxiv","id":"2407.06312","version":2},"attestation_state":"computed","paper":{"title":"Adversarial dynamical systems characterize when data-driven learning succeeds or fails","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","math.OC","math.SP"],"primary_cat":"math.DS","authors_text":"Alexei Stepanenko, Igor Mezi\\'c, Matthew J. Colbrook","submitted_at":"2024-07-08T18:24:48Z","abstract_excerpt":"Many systems resist analytical modeling, making data-driven inference of dynamics important. Yet data-driven methods can fail to converge or generalize, leaving open a central question: When can system behavior be learned reliably from data, and when is such learning impossible? We answer this question using adversarial dynamical systems to identify the boundary between accessible and inaccessible regimes. In Koopman operator learning, a leading framework for representing nonlinear dynamics through linear spectral objects, we design optimal data-driven spectral algorithms with convergence and "},"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":"2407.06312","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.DS","submitted_at":"2024-07-08T18:24:48Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA","math.OC","math.SP"],"title_canon_sha256":"80f0429fabd08ac3dde0243bf21c4a7150ebb07d0e7e3bf6c64a47b0724fb9fa","abstract_canon_sha256":"5d20596dd7fd600f896509a8e8ecceac3c604cec5673ae8993a12ebee3fb299d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:18.791954Z","signature_b64":"bZoPUKHUy24cXhValWzUC4YUDejx2Hm3cP1gLfPdf1mbIbx+dDU9Nw6oRvuhmea7ADbOEaXkPQ43yU01tQzzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a432953fc76cec4173455150508ee031ad587205382675bcb3794a32e3b6a249","last_reissued_at":"2026-06-24T01:14:18.791483Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:18.791483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial dynamical systems characterize when data-driven learning succeeds or fails","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","math.OC","math.SP"],"primary_cat":"math.DS","authors_text":"Alexei Stepanenko, Igor Mezi\\'c, Matthew J. Colbrook","submitted_at":"2024-07-08T18:24:48Z","abstract_excerpt":"Many systems resist analytical modeling, making data-driven inference of dynamics important. Yet data-driven methods can fail to converge or generalize, leaving open a central question: When can system behavior be learned reliably from data, and when is such learning impossible? We answer this question using adversarial dynamical systems to identify the boundary between accessible and inaccessible regimes. In Koopman operator learning, a leading framework for representing nonlinear dynamics through linear spectral objects, we design optimal data-driven spectral algorithms with convergence and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06312","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.06312/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":"2407.06312","created_at":"2026-06-24T01:14:18.791543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.06312v2","created_at":"2026-06-24T01:14:18.791543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06312","created_at":"2026-06-24T01:14:18.791543+00:00"},{"alias_kind":"pith_short_12","alias_value":"UQZJKP6HNTWE","created_at":"2026-06-24T01:14:18.791543+00:00"},{"alias_kind":"pith_short_16","alias_value":"UQZJKP6HNTWEC42F","created_at":"2026-06-24T01:14:18.791543+00:00"},{"alias_kind":"pith_short_8","alias_value":"UQZJKP6H","created_at":"2026-06-24T01:14:18.791543+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2405.07432","citing_title":"Nonparametric Sparse Online Learning of the Koopman Operator","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2502.10918","citing_title":"Signature of glassy dynamics in dynamic modes decompositions","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15234","citing_title":"Sampling pseudospectrum for data-driven matrices","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2509.16016","citing_title":"Residual SCI Upper Bounds And Lower Witnesses For Koopman Approximate Point Spectra In $L^p$ For $1