{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VXUG2K3OHXJ6UDPQMGVV4YCYO5","short_pith_number":"pith:VXUG2K3O","schema_version":"1.0","canonical_sha256":"ade86d2b6e3dd3ea0df061ab5e6058775c6faefdc048c72c653481962d841a9f","source":{"kind":"arxiv","id":"1906.00193","version":1},"attestation_state":"computed","paper":{"title":"A mean-field limit for certain deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","math.PR","stat.TH"],"primary_cat":"math.ST","authors_text":"Daniel Yukimura, Dyego Ara\\'ujo, Roberto I. Oliveira","submitted_at":"2019-06-01T09:51:35Z","abstract_excerpt":"Understanding deep neural networks (DNNs) is a key challenge in the theory of machine learning, with potential applications to the many fields where DNNs have been successfully used. This article presents a scaling limit for a DNN being trained by stochastic gradient descent. Our networks have a fixed (but arbitrary) number $L\\geq 2$ of inner layers; $N\\gg 1$ neurons per layer; full connections between layers; and fixed weights (or \"random features\" that are not trained) near the input and output. Our results describe the evolution of the DNN during training in the limit when $N\\to +\\infty$, w"},"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":"1906.00193","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2019-06-01T09:51:35Z","cross_cats_sorted":["cond-mat.dis-nn","math.PR","stat.TH"],"title_canon_sha256":"339463bfa8589009ec0d12497a6864d76dd92605220a2f06304f9bd569ae51a8","abstract_canon_sha256":"0c019aacecb868d080d66c2ebb1805d3a5f02f6694fe2a93185b4a7e87b97afa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:27.843206Z","signature_b64":"DH4LR0fgUV5sFFXd8nYzYDuuhZtBUQ8Va/NYZQncP4Xi5Q/I/0YYSefDDQAUbDynSBGVkAUo+9A4W4PreXinAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ade86d2b6e3dd3ea0df061ab5e6058775c6faefdc048c72c653481962d841a9f","last_reissued_at":"2026-05-17T23:44:27.842552Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:27.842552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A mean-field limit for certain deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","math.PR","stat.TH"],"primary_cat":"math.ST","authors_text":"Daniel Yukimura, Dyego Ara\\'ujo, Roberto I. Oliveira","submitted_at":"2019-06-01T09:51:35Z","abstract_excerpt":"Understanding deep neural networks (DNNs) is a key challenge in the theory of machine learning, with potential applications to the many fields where DNNs have been successfully used. This article presents a scaling limit for a DNN being trained by stochastic gradient descent. Our networks have a fixed (but arbitrary) number $L\\geq 2$ of inner layers; $N\\gg 1$ neurons per layer; full connections between layers; and fixed weights (or \"random features\" that are not trained) near the input and output. Our results describe the evolution of the DNN during training in the limit when $N\\to +\\infty$, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00193","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":""},"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":"1906.00193","created_at":"2026-05-17T23:44:27.842656+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.00193v1","created_at":"2026-05-17T23:44:27.842656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00193","created_at":"2026-05-17T23:44:27.842656+00:00"},{"alias_kind":"pith_short_12","alias_value":"VXUG2K3OHXJ6","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"VXUG2K3OHXJ6UDPQ","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"VXUG2K3O","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2511.02258","citing_title":"Limit Theorems for Stochastic Gradient Descent in High-Dimensional Single-Layer Networks","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VXUG2K3OHXJ6UDPQMGVV4YCYO5","json":"https://pith.science/pith/VXUG2K3OHXJ6UDPQMGVV4YCYO5.json","graph_json":"https://pith.science/api/pith-number/VXUG2K3OHXJ6UDPQMGVV4YCYO5/graph.json","events_json":"https://pith.science/api/pith-number/VXUG2K3OHXJ6UDPQMGVV4YCYO5/events.json","paper":"https://pith.science/paper/VXUG2K3O"},"agent_actions":{"view_html":"https://pith.science/pith/VXUG2K3OHXJ6UDPQMGVV4YCYO5","download_json":"https://pith.science/pith/VXUG2K3OHXJ6UDPQMGVV4YCYO5.json","view_paper":"https://pith.science/paper/VXUG2K3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.00193&json=true","fetch_graph":"https://pith.science/api/pith-number/VXUG2K3OHXJ6UDPQMGVV4YCYO5/graph.json","fetch_events":"https://pith.science/api/pith-number/VXUG2K3OHXJ6UDPQMGVV4YCYO5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VXUG2K3OHXJ6UDPQMGVV4YCYO5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VXUG2K3OHXJ6UDPQMGVV4YCYO5/action/storage_attestation","attest_author":"https://pith.science/pith/VXUG2K3OHXJ6UDPQMGVV4YCYO5/action/author_attestation","sign_citation":"https://pith.science/pith/VXUG2K3OHXJ6UDPQMGVV4YCYO5/action/citation_signature","submit_replication":"https://pith.science/pith/VXUG2K3OHXJ6UDPQMGVV4YCYO5/action/replication_record"}},"created_at":"2026-05-17T23:44:27.842656+00:00","updated_at":"2026-05-17T23:44:27.842656+00:00"}