{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IC7HFYXDDRJ3SZ5EGFOZMP5KBJ","short_pith_number":"pith:IC7HFYXD","schema_version":"1.0","canonical_sha256":"40be72e2e31c53b967a4315d963faa0a7f9c82eb5a85e10f7d0eee0060d98d70","source":{"kind":"arxiv","id":"2511.08860","version":2},"attestation_state":"computed","paper":{"title":"When is a System Discoverable from Data? Discovery Requires Chaos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NA","math.NA","nlin.CD"],"primary_cat":"math.DS","authors_text":"Carola-Bibiane Sch\\\"onlieb, Gitta Kutyniok, Lior Horesh, Peter Zaika, Philipp Scholl, Zakhar Shumaylov","submitted_at":"2025-11-12T00:35:54Z","abstract_excerpt":"The deep learning revolution has spurred a rise in advances of using AI in sciences. Within physical sciences the main focus has been on discovery of dynamical systems from observational data. Yet the reliability of learned surrogates and symbolic models is often undermined by the fundamental problem of non-uniqueness. The resulting models may fit the available data perfectly, but lack genuine predictive power. This raises the question: under what conditions can the systems governing equations be uniquely identified from a finite set of observations? We show, counter-intuitively, that chaos, t"},"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":"2511.08860","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.DS","submitted_at":"2025-11-12T00:35:54Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NA","math.NA","nlin.CD"],"title_canon_sha256":"108b814a580d16c48ae3ce4e434513d9cd07866db4b847ca5019a2fe38ead21b","abstract_canon_sha256":"fd8e014ffb5b17568d560817738c9153fcdfff88486067d726c0483da25bfc32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:00.541948Z","signature_b64":"/nzNkP8UW04G26Pg1TX0pGj67AlMjJWGpT6ak2rGiG28DqINOr5Eph9h1kuqDV/6ZcPg+xxTaBz4yJBZdlQ6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40be72e2e31c53b967a4315d963faa0a7f9c82eb5a85e10f7d0eee0060d98d70","last_reissued_at":"2026-07-07T01:16:00.541221Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:00.541221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When is a System Discoverable from Data? Discovery Requires Chaos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NA","math.NA","nlin.CD"],"primary_cat":"math.DS","authors_text":"Carola-Bibiane Sch\\\"onlieb, Gitta Kutyniok, Lior Horesh, Peter Zaika, Philipp Scholl, Zakhar Shumaylov","submitted_at":"2025-11-12T00:35:54Z","abstract_excerpt":"The deep learning revolution has spurred a rise in advances of using AI in sciences. Within physical sciences the main focus has been on discovery of dynamical systems from observational data. Yet the reliability of learned surrogates and symbolic models is often undermined by the fundamental problem of non-uniqueness. The resulting models may fit the available data perfectly, but lack genuine predictive power. This raises the question: under what conditions can the systems governing equations be uniquely identified from a finite set of observations? We show, counter-intuitively, that chaos, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.08860","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/2511.08860/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":"2511.08860","created_at":"2026-07-07T01:16:00.541307+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.08860v2","created_at":"2026-07-07T01:16:00.541307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.08860","created_at":"2026-07-07T01:16:00.541307+00:00"},{"alias_kind":"pith_short_12","alias_value":"IC7HFYXDDRJ3","created_at":"2026-07-07T01:16:00.541307+00:00"},{"alias_kind":"pith_short_16","alias_value":"IC7HFYXDDRJ3SZ5E","created_at":"2026-07-07T01:16:00.541307+00:00"},{"alias_kind":"pith_short_8","alias_value":"IC7HFYXD","created_at":"2026-07-07T01:16:00.541307+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2606.12182","citing_title":"How Low Can You Go? Active Learning for Sparse Model Discovery in the Ultra-Low-Data Limit","ref_index":2,"is_internal_anchor":true},{"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":63,"is_internal_anchor":true},{"citing_arxiv_id":"2602.15603","citing_title":"Symbolic recovery of PDEs from measurement data","ref_index":95,"is_internal_anchor":true},{"citing_arxiv_id":"2602.18377","citing_title":"Theory and interpretability of Quantum Extreme Learning Machines: a Pauli-transfer matrix approach","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IC7HFYXDDRJ3SZ5EGFOZMP5KBJ","json":"https://pith.science/pith/IC7HFYXDDRJ3SZ5EGFOZMP5KBJ.json","graph_json":"https://pith.science/api/pith-number/IC7HFYXDDRJ3SZ5EGFOZMP5KBJ/graph.json","events_json":"https://pith.science/api/pith-number/IC7HFYXDDRJ3SZ5EGFOZMP5KBJ/events.json","paper":"https://pith.science/paper/IC7HFYXD"},"agent_actions":{"view_html":"https://pith.science/pith/IC7HFYXDDRJ3SZ5EGFOZMP5KBJ","download_json":"https://pith.science/pith/IC7HFYXDDRJ3SZ5EGFOZMP5KBJ.json","view_paper":"https://pith.science/paper/IC7HFYXD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.08860&json=true","fetch_graph":"https://pith.science/api/pith-number/IC7HFYXDDRJ3SZ5EGFOZMP5KBJ/graph.json","fetch_events":"https://pith.science/api/pith-number/IC7HFYXDDRJ3SZ5EGFOZMP5KBJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IC7HFYXDDRJ3SZ5EGFOZMP5KBJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IC7HFYXDDRJ3SZ5EGFOZMP5KBJ/action/storage_attestation","attest_author":"https://pith.science/pith/IC7HFYXDDRJ3SZ5EGFOZMP5KBJ/action/author_attestation","sign_citation":"https://pith.science/pith/IC7HFYXDDRJ3SZ5EGFOZMP5KBJ/action/citation_signature","submit_replication":"https://pith.science/pith/IC7HFYXDDRJ3SZ5EGFOZMP5KBJ/action/replication_record"}},"created_at":"2026-07-07T01:16:00.541307+00:00","updated_at":"2026-07-07T01:16:00.541307+00:00"}