{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EUBJQTMWMXU64O6XUZPYONVXZ7","short_pith_number":"pith:EUBJQTMW","schema_version":"1.0","canonical_sha256":"2502984d9665e9ee3bd7a65f8736b7cff08c2132058252bdf6e6e6da8062a4ea","source":{"kind":"arxiv","id":"2306.02300","version":1},"attestation_state":"computed","paper":{"title":"How neural networks learn to classify chaotic time series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.DS","authors_text":"Alessandro Corbetta, Thomas Geert de Jong","submitted_at":"2023-06-04T08:53:27Z","abstract_excerpt":"Neural networks are increasingly employed to model, analyze and control non-linear dynamical systems ranging from physics to biology. Owing to their universal approximation capabilities, they regularly outperform state-of-the-art model-driven methods in terms of accuracy, computational speed, and/or control capabilities. On the other hand, neural networks are very often they are taken as black boxes whose explainability is challenged, among others, by huge amounts of trainable parameters. In this paper, we tackle the outstanding issue of analyzing the inner workings of neural networks trained "},"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":"2306.02300","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.DS","submitted_at":"2023-06-04T08:53:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"826dcf229eb5b1724f73bcfdf2ca7bbcfdf4bbfc34c0986b74592ce4b1989796","abstract_canon_sha256":"8b072becd6409fafd020caf9d251b2dcf526029461c8b0673efc3a1adcf86c43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:46.912751Z","signature_b64":"pA4CqCNIuMv7CscRZztGFyR01fsT2j4g/2ymEq1OOQ3sqGnWXpiA8/4TkSnriJC7Kd15Bi0HGD7iYDb2UXCQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2502984d9665e9ee3bd7a65f8736b7cff08c2132058252bdf6e6e6da8062a4ea","last_reissued_at":"2026-07-05T07:27:46.912255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:46.912255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How neural networks learn to classify chaotic time series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.DS","authors_text":"Alessandro Corbetta, Thomas Geert de Jong","submitted_at":"2023-06-04T08:53:27Z","abstract_excerpt":"Neural networks are increasingly employed to model, analyze and control non-linear dynamical systems ranging from physics to biology. Owing to their universal approximation capabilities, they regularly outperform state-of-the-art model-driven methods in terms of accuracy, computational speed, and/or control capabilities. On the other hand, neural networks are very often they are taken as black boxes whose explainability is challenged, among others, by huge amounts of trainable parameters. In this paper, we tackle the outstanding issue of analyzing the inner workings of neural networks trained "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02300","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/2306.02300/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":"2306.02300","created_at":"2026-07-05T07:27:46.912310+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.02300v1","created_at":"2026-07-05T07:27:46.912310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02300","created_at":"2026-07-05T07:27:46.912310+00:00"},{"alias_kind":"pith_short_12","alias_value":"EUBJQTMWMXU6","created_at":"2026-07-05T07:27:46.912310+00:00"},{"alias_kind":"pith_short_16","alias_value":"EUBJQTMWMXU64O6X","created_at":"2026-07-05T07:27:46.912310+00:00"},{"alias_kind":"pith_short_8","alias_value":"EUBJQTMW","created_at":"2026-07-05T07:27:46.912310+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EUBJQTMWMXU64O6XUZPYONVXZ7","json":"https://pith.science/pith/EUBJQTMWMXU64O6XUZPYONVXZ7.json","graph_json":"https://pith.science/api/pith-number/EUBJQTMWMXU64O6XUZPYONVXZ7/graph.json","events_json":"https://pith.science/api/pith-number/EUBJQTMWMXU64O6XUZPYONVXZ7/events.json","paper":"https://pith.science/paper/EUBJQTMW"},"agent_actions":{"view_html":"https://pith.science/pith/EUBJQTMWMXU64O6XUZPYONVXZ7","download_json":"https://pith.science/pith/EUBJQTMWMXU64O6XUZPYONVXZ7.json","view_paper":"https://pith.science/paper/EUBJQTMW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.02300&json=true","fetch_graph":"https://pith.science/api/pith-number/EUBJQTMWMXU64O6XUZPYONVXZ7/graph.json","fetch_events":"https://pith.science/api/pith-number/EUBJQTMWMXU64O6XUZPYONVXZ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EUBJQTMWMXU64O6XUZPYONVXZ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EUBJQTMWMXU64O6XUZPYONVXZ7/action/storage_attestation","attest_author":"https://pith.science/pith/EUBJQTMWMXU64O6XUZPYONVXZ7/action/author_attestation","sign_citation":"https://pith.science/pith/EUBJQTMWMXU64O6XUZPYONVXZ7/action/citation_signature","submit_replication":"https://pith.science/pith/EUBJQTMWMXU64O6XUZPYONVXZ7/action/replication_record"}},"created_at":"2026-07-05T07:27:46.912310+00:00","updated_at":"2026-07-05T07:27:46.912310+00:00"}