{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4QLEAV62UU3C2T7XMC5NTSFTZG","short_pith_number":"pith:4QLEAV62","schema_version":"1.0","canonical_sha256":"e4164057daa5362d4ff760bad9c8b3c9bd4626dded6538f1f7b41480523e653f","source":{"kind":"arxiv","id":"2306.16830","version":2},"attestation_state":"computed","paper":{"title":"Sampling weights of deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Chinmay Datar, Erik Lien Bolager, Felix Dietrich, Iryna Burak, Qing Sun","submitted_at":"2023-06-29T10:13:36Z","abstract_excerpt":"We introduce a probability distribution, combined with an efficient sampling algorithm, for weights and biases of fully-connected neural networks. In a supervised learning context, no iterative optimization or gradient computations of internal network parameters are needed to obtain a trained network. The sampling is based on the idea of random feature models. However, instead of a data-agnostic distribution, e.g., a normal distribution, we use both the input and the output training data to sample shallow and deep networks. We prove that sampled networks are universal approximators. For Barron"},"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":"2306.16830","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-29T10:13:36Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"6a224cde0f5936c5a0c805fb04d1b9f800be4a5afa5e061493b207b22947e5f0","abstract_canon_sha256":"677944ad7a9519a6fc3d754adae3c09e21ebdfcc46d53ba52d9a105f8b8a4b61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:57.103285Z","signature_b64":"gEyCP9FlXq8hJr8Xnhb+byo/7f4/JD9I1FQOanh1awNlp0B6kJ7+6+c0cFyVBwIh2BrYl08RVFThDaUrihHiAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4164057daa5362d4ff760bad9c8b3c9bd4626dded6538f1f7b41480523e653f","last_reissued_at":"2026-07-05T07:11:57.102725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:57.102725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sampling weights of deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Chinmay Datar, Erik Lien Bolager, Felix Dietrich, Iryna Burak, Qing Sun","submitted_at":"2023-06-29T10:13:36Z","abstract_excerpt":"We introduce a probability distribution, combined with an efficient sampling algorithm, for weights and biases of fully-connected neural networks. In a supervised learning context, no iterative optimization or gradient computations of internal network parameters are needed to obtain a trained network. The sampling is based on the idea of random feature models. However, instead of a data-agnostic distribution, e.g., a normal distribution, we use both the input and the output training data to sample shallow and deep networks. We prove that sampled networks are universal approximators. For Barron"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.16830","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/2306.16830/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":"2306.16830","created_at":"2026-07-05T07:11:57.102786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.16830v2","created_at":"2026-07-05T07:11:57.102786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16830","created_at":"2026-07-05T07:11:57.102786+00:00"},{"alias_kind":"pith_short_12","alias_value":"4QLEAV62UU3C","created_at":"2026-07-05T07:11:57.102786+00:00"},{"alias_kind":"pith_short_16","alias_value":"4QLEAV62UU3C2T7X","created_at":"2026-07-05T07:11:57.102786+00:00"},{"alias_kind":"pith_short_8","alias_value":"4QLEAV62","created_at":"2026-07-05T07:11:57.102786+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/4QLEAV62UU3C2T7XMC5NTSFTZG","json":"https://pith.science/pith/4QLEAV62UU3C2T7XMC5NTSFTZG.json","graph_json":"https://pith.science/api/pith-number/4QLEAV62UU3C2T7XMC5NTSFTZG/graph.json","events_json":"https://pith.science/api/pith-number/4QLEAV62UU3C2T7XMC5NTSFTZG/events.json","paper":"https://pith.science/paper/4QLEAV62"},"agent_actions":{"view_html":"https://pith.science/pith/4QLEAV62UU3C2T7XMC5NTSFTZG","download_json":"https://pith.science/pith/4QLEAV62UU3C2T7XMC5NTSFTZG.json","view_paper":"https://pith.science/paper/4QLEAV62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.16830&json=true","fetch_graph":"https://pith.science/api/pith-number/4QLEAV62UU3C2T7XMC5NTSFTZG/graph.json","fetch_events":"https://pith.science/api/pith-number/4QLEAV62UU3C2T7XMC5NTSFTZG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4QLEAV62UU3C2T7XMC5NTSFTZG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4QLEAV62UU3C2T7XMC5NTSFTZG/action/storage_attestation","attest_author":"https://pith.science/pith/4QLEAV62UU3C2T7XMC5NTSFTZG/action/author_attestation","sign_citation":"https://pith.science/pith/4QLEAV62UU3C2T7XMC5NTSFTZG/action/citation_signature","submit_replication":"https://pith.science/pith/4QLEAV62UU3C2T7XMC5NTSFTZG/action/replication_record"}},"created_at":"2026-07-05T07:11:57.102786+00:00","updated_at":"2026-07-05T07:11:57.102786+00:00"}