{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QAEVMT75Q3P6FE4E4D4NIJLBWT","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":"35be85174bfb2f12fcc260f0d52782d6de6c98b70f5ac50de14267ce9eea935a","cross_cats_sorted":["cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T21:24:34Z","title_canon_sha256":"b96acc8f530798343b3925abe5aaf04e8bd81646a19226c5a44b4b1f07609e09"},"schema_version":"1.0","source":{"id":"2410.23467","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23467","created_at":"2026-07-05T10:06:45Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23467v2","created_at":"2026-07-05T10:06:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23467","created_at":"2026-07-05T10:06:45Z"},{"alias_kind":"pith_short_12","alias_value":"QAEVMT75Q3P6","created_at":"2026-07-05T10:06:45Z"},{"alias_kind":"pith_short_16","alias_value":"QAEVMT75Q3P6FE4E","created_at":"2026-07-05T10:06:45Z"},{"alias_kind":"pith_short_8","alias_value":"QAEVMT75","created_at":"2026-07-05T10:06:45Z"}],"graph_snapshots":[{"event_id":"sha256:cda9cc29a28d4b0853fa96398f1da1d0654618ae12d6e2114d0df557566a6e2f","target":"graph","created_at":"2026-07-05T10:06:45Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.23467/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recurrent neural networks are a successful neural architecture for many time-dependent problems, including time series analysis, forecasting, and modeling of dynamical systems. Training such networks with backpropagation through time is a notoriously difficult problem because their loss gradients tend to explode or vanish. In this contribution, we introduce a computational approach to construct all weights and biases of a recurrent neural network without using gradient-based methods. The approach is based on a combination of random feature networks and Koopman operator theory for dynamical sys","authors_text":"Ana Cukarska, Erik Lien Bolager, Felix Dietrich, Iryna Burak, Zahra Monfared","cross_cats":["cs.NA","math.NA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T21:24:34Z","title":"Gradient-free training of recurrent neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23467","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:86b7bac58604ba0f05d2abcc2b2885b54cc75c123249c1de71bac17919c2d9ca","target":"record","created_at":"2026-07-05T10:06:45Z","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":"35be85174bfb2f12fcc260f0d52782d6de6c98b70f5ac50de14267ce9eea935a","cross_cats_sorted":["cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T21:24:34Z","title_canon_sha256":"b96acc8f530798343b3925abe5aaf04e8bd81646a19226c5a44b4b1f07609e09"},"schema_version":"1.0","source":{"id":"2410.23467","kind":"arxiv","version":2}},"canonical_sha256":"8009564ffd86dfe29384e0f8d42561b4f398ba6307dabfcb7b0cd470a49d57da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8009564ffd86dfe29384e0f8d42561b4f398ba6307dabfcb7b0cd470a49d57da","first_computed_at":"2026-07-05T10:06:45.418055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:06:45.418055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E8rPsqpbAZ71wKW3aJ3VjhBUHSeVpE8+uWnFti2lPnJ415Ig/Z5ALgGMgbNf96tHD2EqI/yr5FStgOaDgd9YAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:06:45.418586Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.23467","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86b7bac58604ba0f05d2abcc2b2885b54cc75c123249c1de71bac17919c2d9ca","sha256:cda9cc29a28d4b0853fa96398f1da1d0654618ae12d6e2114d0df557566a6e2f"],"state_sha256":"dee594e6b17b3b282c2e90637289902081dc20d468ecaeeb83240dd8350a37b9"}