{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JXEAKVLL6EDPWE7NLEF6XJOBF5","short_pith_number":"pith:JXEAKVLL","schema_version":"1.0","canonical_sha256":"4dc805556bf106fb13ed590beba5c12f411dd46f4d8ec626749d25cdb3d42c1c","source":{"kind":"arxiv","id":"2402.00152","version":5},"attestation_state":"computed","paper":{"title":"Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Juncai He, Yahong Yang","submitted_at":"2024-01-31T20:10:10Z","abstract_excerpt":"Constructing the architecture of a neural network is a challenging pursuit for the machine learning community, and the dilemma of whether to go deeper or wider remains a persistent question. This paper explores a comparison between deeper neural networks (DeNNs) with a flexible number of layers and wider neural networks (WeNNs) with limited hidden layers, focusing on their optimal generalization error in Sobolev losses. Analytical investigations reveal that the architecture of a neural network can be significantly influenced by various factors, including the number of sample points, parameters"},"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":"2402.00152","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-31T20:10:10Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"15251515dc8f8099a1c0fc5065a4979c0b2ef0a5ec902965a46d09dc3d0145ef","abstract_canon_sha256":"6a07b07791dc99eca81b23be1879970ac06fc47d82fd48e1b978bdb5b626c40a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:55.266324Z","signature_b64":"ikUhzkSpJkLm/hEK4J7YygUgbTjSN5k1z19k0jMJl0y6lZOOrQpwWBPMAFL+qs/qUyoRa+llsUxlWlIFHgasBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4dc805556bf106fb13ed590beba5c12f411dd46f4d8ec626749d25cdb3d42c1c","last_reissued_at":"2026-06-10T01:10:55.265872Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:55.265872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Juncai He, Yahong Yang","submitted_at":"2024-01-31T20:10:10Z","abstract_excerpt":"Constructing the architecture of a neural network is a challenging pursuit for the machine learning community, and the dilemma of whether to go deeper or wider remains a persistent question. This paper explores a comparison between deeper neural networks (DeNNs) with a flexible number of layers and wider neural networks (WeNNs) with limited hidden layers, focusing on their optimal generalization error in Sobolev losses. Analytical investigations reveal that the architecture of a neural network can be significantly influenced by various factors, including the number of sample points, parameters"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00152","kind":"arxiv","version":5},"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/2402.00152/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":"2402.00152","created_at":"2026-06-10T01:10:55.265932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.00152v5","created_at":"2026-06-10T01:10:55.265932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00152","created_at":"2026-06-10T01:10:55.265932+00:00"},{"alias_kind":"pith_short_12","alias_value":"JXEAKVLL6EDP","created_at":"2026-06-10T01:10:55.265932+00:00"},{"alias_kind":"pith_short_16","alias_value":"JXEAKVLL6EDPWE7N","created_at":"2026-06-10T01:10:55.265932+00:00"},{"alias_kind":"pith_short_8","alias_value":"JXEAKVLL","created_at":"2026-06-10T01:10:55.265932+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/JXEAKVLL6EDPWE7NLEF6XJOBF5","json":"https://pith.science/pith/JXEAKVLL6EDPWE7NLEF6XJOBF5.json","graph_json":"https://pith.science/api/pith-number/JXEAKVLL6EDPWE7NLEF6XJOBF5/graph.json","events_json":"https://pith.science/api/pith-number/JXEAKVLL6EDPWE7NLEF6XJOBF5/events.json","paper":"https://pith.science/paper/JXEAKVLL"},"agent_actions":{"view_html":"https://pith.science/pith/JXEAKVLL6EDPWE7NLEF6XJOBF5","download_json":"https://pith.science/pith/JXEAKVLL6EDPWE7NLEF6XJOBF5.json","view_paper":"https://pith.science/paper/JXEAKVLL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.00152&json=true","fetch_graph":"https://pith.science/api/pith-number/JXEAKVLL6EDPWE7NLEF6XJOBF5/graph.json","fetch_events":"https://pith.science/api/pith-number/JXEAKVLL6EDPWE7NLEF6XJOBF5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JXEAKVLL6EDPWE7NLEF6XJOBF5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JXEAKVLL6EDPWE7NLEF6XJOBF5/action/storage_attestation","attest_author":"https://pith.science/pith/JXEAKVLL6EDPWE7NLEF6XJOBF5/action/author_attestation","sign_citation":"https://pith.science/pith/JXEAKVLL6EDPWE7NLEF6XJOBF5/action/citation_signature","submit_replication":"https://pith.science/pith/JXEAKVLL6EDPWE7NLEF6XJOBF5/action/replication_record"}},"created_at":"2026-06-10T01:10:55.265932+00:00","updated_at":"2026-06-10T01:10:55.265932+00:00"}