{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JZUN3RDEFK7WHJHEFMUWTFKG6R","short_pith_number":"pith:JZUN3RDE","schema_version":"1.0","canonical_sha256":"4e68ddc4642abf63a4e42b29699546f47ec51952c3612ec4869e04920b1879ed","source":{"kind":"arxiv","id":"2605.25057","version":1},"attestation_state":"computed","paper":{"title":"Random Neural Network Expressivity for Non-Linear Partial Differential Equations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Lukas Gonon, Muhammed Ali Mehmood","submitted_at":"2026-05-24T13:08:34Z","abstract_excerpt":"Neural networks with randomly generated hidden weights (RaNNs) have been extensively studied, both as a standalone learning method and as an initialization for fully trainable deep learning methods. In this work, we study RaNN expressivity for learning solutions to non-linear partial differential equations (PDEs). Despite their widespread use in practical applications, a rigorous theoretical understanding of the approximation properties of RaNNs in this context remains limited. Here, we derive error bounds for RaNN approximations to time-dependent Sobolev functions and obtain a dimension-free "},"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":"2605.25057","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2026-05-24T13:08:34Z","cross_cats_sorted":["cs.LG","cs.NA"],"title_canon_sha256":"bdc4a69cced4f2a1bc39856749e1c2ee385fb60594a10d89c3569c6a2c11893c","abstract_canon_sha256":"736b407f5ec828e33198c588157e669505eb56d4724e15bf15a6ac0cd3754598"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:03:37.809226Z","signature_b64":"P089Wmpr4QU7xYK14b4FC+Vb4fzsCzwB0ywjBYPKTcisPdlyKj0+03c6pv4A4k+nzWPvx/tv5TWrESMLA7m7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e68ddc4642abf63a4e42b29699546f47ec51952c3612ec4869e04920b1879ed","last_reissued_at":"2026-05-26T02:03:37.808289Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:03:37.808289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Random Neural Network Expressivity for Non-Linear Partial Differential Equations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Lukas Gonon, Muhammed Ali Mehmood","submitted_at":"2026-05-24T13:08:34Z","abstract_excerpt":"Neural networks with randomly generated hidden weights (RaNNs) have been extensively studied, both as a standalone learning method and as an initialization for fully trainable deep learning methods. In this work, we study RaNN expressivity for learning solutions to non-linear partial differential equations (PDEs). Despite their widespread use in practical applications, a rigorous theoretical understanding of the approximation properties of RaNNs in this context remains limited. Here, we derive error bounds for RaNN approximations to time-dependent Sobolev functions and obtain a dimension-free "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25057","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/2605.25057/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":"2605.25057","created_at":"2026-05-26T02:03:37.808440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25057v1","created_at":"2026-05-26T02:03:37.808440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25057","created_at":"2026-05-26T02:03:37.808440+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZUN3RDEFK7W","created_at":"2026-05-26T02:03:37.808440+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZUN3RDEFK7WHJHE","created_at":"2026-05-26T02:03:37.808440+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZUN3RDE","created_at":"2026-05-26T02:03:37.808440+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/JZUN3RDEFK7WHJHEFMUWTFKG6R","json":"https://pith.science/pith/JZUN3RDEFK7WHJHEFMUWTFKG6R.json","graph_json":"https://pith.science/api/pith-number/JZUN3RDEFK7WHJHEFMUWTFKG6R/graph.json","events_json":"https://pith.science/api/pith-number/JZUN3RDEFK7WHJHEFMUWTFKG6R/events.json","paper":"https://pith.science/paper/JZUN3RDE"},"agent_actions":{"view_html":"https://pith.science/pith/JZUN3RDEFK7WHJHEFMUWTFKG6R","download_json":"https://pith.science/pith/JZUN3RDEFK7WHJHEFMUWTFKG6R.json","view_paper":"https://pith.science/paper/JZUN3RDE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25057&json=true","fetch_graph":"https://pith.science/api/pith-number/JZUN3RDEFK7WHJHEFMUWTFKG6R/graph.json","fetch_events":"https://pith.science/api/pith-number/JZUN3RDEFK7WHJHEFMUWTFKG6R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZUN3RDEFK7WHJHEFMUWTFKG6R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZUN3RDEFK7WHJHEFMUWTFKG6R/action/storage_attestation","attest_author":"https://pith.science/pith/JZUN3RDEFK7WHJHEFMUWTFKG6R/action/author_attestation","sign_citation":"https://pith.science/pith/JZUN3RDEFK7WHJHEFMUWTFKG6R/action/citation_signature","submit_replication":"https://pith.science/pith/JZUN3RDEFK7WHJHEFMUWTFKG6R/action/replication_record"}},"created_at":"2026-05-26T02:03:37.808440+00:00","updated_at":"2026-05-26T02:03:37.808440+00:00"}