{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SRHRNFXI4JYINVH4PHV3DK4PSQ","short_pith_number":"pith:SRHRNFXI","schema_version":"1.0","canonical_sha256":"944f1696e8e27086d4fc79ebb1ab8f941b8b1b819617727c6f92c0c823b26f27","source":{"kind":"arxiv","id":"1907.04108","version":3},"attestation_state":"computed","paper":{"title":"Scaling Limit of Neural Networks with the Xavier Initialization and Convergence to a Global Minimum","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.PR","authors_text":"Justin Sirignano, Konstantinos Spiliopoulos","submitted_at":"2019-07-09T12:17:03Z","abstract_excerpt":"We analyze single-layer neural networks with the Xavier initialization in the asymptotic regime of large numbers of hidden units and large numbers of stochastic gradient descent training steps. The evolution of the neural network during training can be viewed as a stochastic system and, using techniques from stochastic analysis, we prove the neural network converges in distribution to a random ODE with a Gaussian distribution. The limit is completely different than in the typical mean-field results for neural networks due to the $\\frac{1}{\\sqrt{N}}$ normalization factor in the Xavier initializ"},"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":"1907.04108","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.PR","submitted_at":"2019-07-09T12:17:03Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"e114eb2c05a5fa8cd9a773196cafe645bd49fd8d233a5889c4ed9d4581ab7f87","abstract_canon_sha256":"00a9a55e231f3aa47e6b851739b2d35f7a719e2d770e3548db6e5559c1e5f069"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:20.298806Z","signature_b64":"uhzYFr4wlNueeSgaxeVCUV65PzkC1aKQOvmHctHXTPDt+h0aqb5gGoTMGZVwREIe+nEOPWH+Aki1WUdqlc4XAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"944f1696e8e27086d4fc79ebb1ab8f941b8b1b819617727c6f92c0c823b26f27","last_reissued_at":"2026-07-05T04:13:20.298381Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:20.298381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Limit of Neural Networks with the Xavier Initialization and Convergence to a Global Minimum","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.PR","authors_text":"Justin Sirignano, Konstantinos Spiliopoulos","submitted_at":"2019-07-09T12:17:03Z","abstract_excerpt":"We analyze single-layer neural networks with the Xavier initialization in the asymptotic regime of large numbers of hidden units and large numbers of stochastic gradient descent training steps. The evolution of the neural network during training can be viewed as a stochastic system and, using techniques from stochastic analysis, we prove the neural network converges in distribution to a random ODE with a Gaussian distribution. The limit is completely different than in the typical mean-field results for neural networks due to the $\\frac{1}{\\sqrt{N}}$ normalization factor in the Xavier initializ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04108","kind":"arxiv","version":3},"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/1907.04108/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":"1907.04108","created_at":"2026-07-05T04:13:20.298439+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.04108v3","created_at":"2026-07-05T04:13:20.298439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04108","created_at":"2026-07-05T04:13:20.298439+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRHRNFXI4JYI","created_at":"2026-07-05T04:13:20.298439+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRHRNFXI4JYINVH4","created_at":"2026-07-05T04:13:20.298439+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRHRNFXI","created_at":"2026-07-05T04:13:20.298439+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08352","citing_title":"Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08352","citing_title":"Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SRHRNFXI4JYINVH4PHV3DK4PSQ","json":"https://pith.science/pith/SRHRNFXI4JYINVH4PHV3DK4PSQ.json","graph_json":"https://pith.science/api/pith-number/SRHRNFXI4JYINVH4PHV3DK4PSQ/graph.json","events_json":"https://pith.science/api/pith-number/SRHRNFXI4JYINVH4PHV3DK4PSQ/events.json","paper":"https://pith.science/paper/SRHRNFXI"},"agent_actions":{"view_html":"https://pith.science/pith/SRHRNFXI4JYINVH4PHV3DK4PSQ","download_json":"https://pith.science/pith/SRHRNFXI4JYINVH4PHV3DK4PSQ.json","view_paper":"https://pith.science/paper/SRHRNFXI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.04108&json=true","fetch_graph":"https://pith.science/api/pith-number/SRHRNFXI4JYINVH4PHV3DK4PSQ/graph.json","fetch_events":"https://pith.science/api/pith-number/SRHRNFXI4JYINVH4PHV3DK4PSQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRHRNFXI4JYINVH4PHV3DK4PSQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRHRNFXI4JYINVH4PHV3DK4PSQ/action/storage_attestation","attest_author":"https://pith.science/pith/SRHRNFXI4JYINVH4PHV3DK4PSQ/action/author_attestation","sign_citation":"https://pith.science/pith/SRHRNFXI4JYINVH4PHV3DK4PSQ/action/citation_signature","submit_replication":"https://pith.science/pith/SRHRNFXI4JYINVH4PHV3DK4PSQ/action/replication_record"}},"created_at":"2026-07-05T04:13:20.298439+00:00","updated_at":"2026-07-05T04:13:20.298439+00:00"}