{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TQCY3GVKLSI3XBHFDBSR4HYZFZ","short_pith_number":"pith:TQCY3GVK","schema_version":"1.0","canonical_sha256":"9c058d9aaa5c91bb84e518651e1f192e444f972dbca03c6e10ce2b931d262cc5","source":{"kind":"arxiv","id":"1902.04760","version":3},"attestation_state":"computed","paper":{"title":"Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.LG","math-ph","math.MP","stat.ML"],"primary_cat":"cs.NE","authors_text":"Greg Yang","submitted_at":"2019-02-13T06:09:18Z","abstract_excerpt":"Several recent trends in machine learning theory and practice, from the design of state-of-the-art Gaussian Process to the convergence analysis of deep neural nets (DNNs) under stochastic gradient descent (SGD), have found it fruitful to study wide random neural networks. Central to these approaches are certain scaling limits of such networks. We unify these results by introducing a notion of a straightline \\emph{tensor program} that can express most neural network computations, and we characterize its scaling limit when its tensors are large and randomized. From our framework follows (1) the "},"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":"1902.04760","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-02-13T06:09:18Z","cross_cats_sorted":["cond-mat.dis-nn","cs.LG","math-ph","math.MP","stat.ML"],"title_canon_sha256":"5a30829625fcf7b8eea04073969664bbb6bf4b29ad69bdd0e0e8a66985506cad","abstract_canon_sha256":"0a52ffc4e34bc602b0c46f434ede866a5b825dd9d70f669c698a8614eb96311c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:52:45.358136Z","signature_b64":"+624lFxiF/PJW8ZmMmgwfaNJSD7aHkez6dFT+O15Uu3uMn9SrcD5RX7JURPMnt1GBLZ+YQsdELTzbR8ElZ7cBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c058d9aaa5c91bb84e518651e1f192e444f972dbca03c6e10ce2b931d262cc5","last_reissued_at":"2026-07-05T00:52:45.357718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:52:45.357718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.LG","math-ph","math.MP","stat.ML"],"primary_cat":"cs.NE","authors_text":"Greg Yang","submitted_at":"2019-02-13T06:09:18Z","abstract_excerpt":"Several recent trends in machine learning theory and practice, from the design of state-of-the-art Gaussian Process to the convergence analysis of deep neural nets (DNNs) under stochastic gradient descent (SGD), have found it fruitful to study wide random neural networks. Central to these approaches are certain scaling limits of such networks. We unify these results by introducing a notion of a straightline \\emph{tensor program} that can express most neural network computations, and we characterize its scaling limit when its tensors are large and randomized. From our framework follows (1) the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04760","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/1902.04760/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":"1902.04760","created_at":"2026-07-05T00:52:45.357781+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.04760v3","created_at":"2026-07-05T00:52:45.357781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04760","created_at":"2026-07-05T00:52:45.357781+00:00"},{"alias_kind":"pith_short_12","alias_value":"TQCY3GVKLSI3","created_at":"2026-07-05T00:52:45.357781+00:00"},{"alias_kind":"pith_short_16","alias_value":"TQCY3GVKLSI3XBHF","created_at":"2026-07-05T00:52:45.357781+00:00"},{"alias_kind":"pith_short_8","alias_value":"TQCY3GVK","created_at":"2026-07-05T00:52:45.357781+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08218","citing_title":"How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04426","citing_title":"Discrete signaling mediates chaotic regularization in recurrent neural networks","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30831","citing_title":"Geometric Dyson Brownian Motions and the Free Log-Normal Limit for a Non-Square Gaussian Matrix Product","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2508.03810","citing_title":"Viability of perturbative expansion for quantum field theories on neurons","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17968","citing_title":"Function graph transformers universally approximate operators between function spaces","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05113","citing_title":"How Long Does Infinite Width Last? Signal Propagation in Long-Range Linear Recurrences","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TQCY3GVKLSI3XBHFDBSR4HYZFZ","json":"https://pith.science/pith/TQCY3GVKLSI3XBHFDBSR4HYZFZ.json","graph_json":"https://pith.science/api/pith-number/TQCY3GVKLSI3XBHFDBSR4HYZFZ/graph.json","events_json":"https://pith.science/api/pith-number/TQCY3GVKLSI3XBHFDBSR4HYZFZ/events.json","paper":"https://pith.science/paper/TQCY3GVK"},"agent_actions":{"view_html":"https://pith.science/pith/TQCY3GVKLSI3XBHFDBSR4HYZFZ","download_json":"https://pith.science/pith/TQCY3GVKLSI3XBHFDBSR4HYZFZ.json","view_paper":"https://pith.science/paper/TQCY3GVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.04760&json=true","fetch_graph":"https://pith.science/api/pith-number/TQCY3GVKLSI3XBHFDBSR4HYZFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TQCY3GVKLSI3XBHFDBSR4HYZFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TQCY3GVKLSI3XBHFDBSR4HYZFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TQCY3GVKLSI3XBHFDBSR4HYZFZ/action/storage_attestation","attest_author":"https://pith.science/pith/TQCY3GVKLSI3XBHFDBSR4HYZFZ/action/author_attestation","sign_citation":"https://pith.science/pith/TQCY3GVKLSI3XBHFDBSR4HYZFZ/action/citation_signature","submit_replication":"https://pith.science/pith/TQCY3GVKLSI3XBHFDBSR4HYZFZ/action/replication_record"}},"created_at":"2026-07-05T00:52:45.357781+00:00","updated_at":"2026-07-05T00:52:45.357781+00:00"}