{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JBJWRPKR64KEGFJY6PAWN4EBXG","short_pith_number":"pith:JBJWRPKR","schema_version":"1.0","canonical_sha256":"485368bd51f714431538f3c166f081b9bd9fff202319d06c5e0800aa3ef8b5ce","source":{"kind":"arxiv","id":"2002.05933","version":2},"attestation_state":"computed","paper":{"title":"Approximation Bounds for Random Neural Networks and Reservoir Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","cs.SY","eess.SY"],"primary_cat":"math.PR","authors_text":"Juan-Pablo Ortega, Lukas Gonon, Lyudmila Grigoryeva","submitted_at":"2020-02-14T09:43:28Z","abstract_excerpt":"This work studies approximation based on single-hidden-layer feedforward and recurrent neural networks with randomly generated internal weights. These methods, in which only the last layer of weights and a few hyperparameters are optimized, have been successfully applied in a wide range of static and dynamic learning problems. Despite the popularity of this approach in empirical tasks, important theoretical questions regarding the relation between the unknown function, the weight distribution, and the approximation rate have remained open. In this work it is proved that, as long as the unknown"},"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":"2002.05933","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.PR","submitted_at":"2020-02-14T09:43:28Z","cross_cats_sorted":["cs.NE","cs.SY","eess.SY"],"title_canon_sha256":"2ec536cb0f7b7752883e1f792bce61a6673a098a8827b36c5a0b99317c3c89c9","abstract_canon_sha256":"e9e76c65d2ea9307f5adef36f11ada5b3a056d5f12480543ce27d27790e3f832"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:15:22.549095Z","signature_b64":"wkGBti41E+mCZChRlg5+N9wE/Fo5mTK26VaxlvM9ZaBd5A6gajQcTfOtSOl3/59vu115bWpVpl60Hj9aSYUhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"485368bd51f714431538f3c166f081b9bd9fff202319d06c5e0800aa3ef8b5ce","last_reissued_at":"2026-07-05T02:15:22.548702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:15:22.548702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approximation Bounds for Random Neural Networks and Reservoir Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","cs.SY","eess.SY"],"primary_cat":"math.PR","authors_text":"Juan-Pablo Ortega, Lukas Gonon, Lyudmila Grigoryeva","submitted_at":"2020-02-14T09:43:28Z","abstract_excerpt":"This work studies approximation based on single-hidden-layer feedforward and recurrent neural networks with randomly generated internal weights. These methods, in which only the last layer of weights and a few hyperparameters are optimized, have been successfully applied in a wide range of static and dynamic learning problems. Despite the popularity of this approach in empirical tasks, important theoretical questions regarding the relation between the unknown function, the weight distribution, and the approximation rate have remained open. In this work it is proved that, as long as the unknown"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05933","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/2002.05933/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":"2002.05933","created_at":"2026-07-05T02:15:22.548761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.05933v2","created_at":"2026-07-05T02:15:22.548761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05933","created_at":"2026-07-05T02:15:22.548761+00:00"},{"alias_kind":"pith_short_12","alias_value":"JBJWRPKR64KE","created_at":"2026-07-05T02:15:22.548761+00:00"},{"alias_kind":"pith_short_16","alias_value":"JBJWRPKR64KEGFJY","created_at":"2026-07-05T02:15:22.548761+00:00"},{"alias_kind":"pith_short_8","alias_value":"JBJWRPKR","created_at":"2026-07-05T02:15:22.548761+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.05202","citing_title":"Embedding and Approximation Theorems for Echo State Networks","ref_index":75,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JBJWRPKR64KEGFJY6PAWN4EBXG","json":"https://pith.science/pith/JBJWRPKR64KEGFJY6PAWN4EBXG.json","graph_json":"https://pith.science/api/pith-number/JBJWRPKR64KEGFJY6PAWN4EBXG/graph.json","events_json":"https://pith.science/api/pith-number/JBJWRPKR64KEGFJY6PAWN4EBXG/events.json","paper":"https://pith.science/paper/JBJWRPKR"},"agent_actions":{"view_html":"https://pith.science/pith/JBJWRPKR64KEGFJY6PAWN4EBXG","download_json":"https://pith.science/pith/JBJWRPKR64KEGFJY6PAWN4EBXG.json","view_paper":"https://pith.science/paper/JBJWRPKR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.05933&json=true","fetch_graph":"https://pith.science/api/pith-number/JBJWRPKR64KEGFJY6PAWN4EBXG/graph.json","fetch_events":"https://pith.science/api/pith-number/JBJWRPKR64KEGFJY6PAWN4EBXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JBJWRPKR64KEGFJY6PAWN4EBXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JBJWRPKR64KEGFJY6PAWN4EBXG/action/storage_attestation","attest_author":"https://pith.science/pith/JBJWRPKR64KEGFJY6PAWN4EBXG/action/author_attestation","sign_citation":"https://pith.science/pith/JBJWRPKR64KEGFJY6PAWN4EBXG/action/citation_signature","submit_replication":"https://pith.science/pith/JBJWRPKR64KEGFJY6PAWN4EBXG/action/replication_record"}},"created_at":"2026-07-05T02:15:22.548761+00:00","updated_at":"2026-07-05T02:15:22.548761+00:00"}