{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:L6VR5NL2EKXULRGKACQ7QB4FLM","short_pith_number":"pith:L6VR5NL2","schema_version":"1.0","canonical_sha256":"5fab1eb57a22af45c4ca00a1f807855b2924ad7144ad783114c7a7790ae85c1a","source":{"kind":"arxiv","id":"1804.11271","version":2},"attestation_state":"computed","paper":{"title":"Gaussian Process Behaviour in Wide Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander G. de G. Matthews, Jiri Hron, Mark Rowland, Richard E. Turner, Zoubin Ghahramani","submitted_at":"2018-04-30T15:21:23Z","abstract_excerpt":"Whilst deep neural networks have shown great empirical success, there is still much work to be done to understand their theoretical properties. In this paper, we study the relationship between random, wide, fully connected, feedforward networks with more than one hidden layer and Gaussian processes with a recursive kernel definition. We show that, under broad conditions, as we make the architecture increasingly wide, the implied random function converges in distribution to a Gaussian process, formalising and extending existing results by Neal (1996) to deep networks. To evaluate convergence ra"},"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":"1804.11271","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-30T15:21:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9da5efbbebb72d16786436d83fdc07be7a7e3237d976bdb1cf137af91c6cfb98","abstract_canon_sha256":"945992acc987a0bbfc3dc994e00d26e277deaa1da91cdfaefb1902c8311d27c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:00.380257Z","signature_b64":"BlbltOJKN+VTzKfYEMek83C2MKoI3OSrfVZCkXcol+Gl9cqE3Xu6+VxaMAkLvuubIrw+f8Jiyir0tVOxpGIpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fab1eb57a22af45c4ca00a1f807855b2924ad7144ad783114c7a7790ae85c1a","last_reissued_at":"2026-05-18T00:08:00.379734Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:00.379734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaussian Process Behaviour in Wide Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander G. de G. Matthews, Jiri Hron, Mark Rowland, Richard E. Turner, Zoubin Ghahramani","submitted_at":"2018-04-30T15:21:23Z","abstract_excerpt":"Whilst deep neural networks have shown great empirical success, there is still much work to be done to understand their theoretical properties. In this paper, we study the relationship between random, wide, fully connected, feedforward networks with more than one hidden layer and Gaussian processes with a recursive kernel definition. We show that, under broad conditions, as we make the architecture increasingly wide, the implied random function converges in distribution to a Gaussian process, formalising and extending existing results by Neal (1996) to deep networks. To evaluate convergence ra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.11271","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":""},"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":"1804.11271","created_at":"2026-05-18T00:08:00.379815+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.11271v2","created_at":"2026-05-18T00:08:00.379815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.11271","created_at":"2026-05-18T00:08:00.379815+00:00"},{"alias_kind":"pith_short_12","alias_value":"L6VR5NL2EKXU","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"L6VR5NL2EKXULRGK","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"L6VR5NL2","created_at":"2026-05-18T12:32:33.847187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2508.03810","citing_title":"Viability of perturbative expansion for quantum field theories on neurons","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17606","citing_title":"The Neural Tangent Kernel for Classification","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27050","citing_title":"Optimal Architecture and Fundamental Bounds in Neural Network Field Theory","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26898","citing_title":"Stochastic Scaling Limits and Synchronization by Noise in Deep Transformer Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04901","citing_title":"On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference","ref_index":59,"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":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L6VR5NL2EKXULRGKACQ7QB4FLM","json":"https://pith.science/pith/L6VR5NL2EKXULRGKACQ7QB4FLM.json","graph_json":"https://pith.science/api/pith-number/L6VR5NL2EKXULRGKACQ7QB4FLM/graph.json","events_json":"https://pith.science/api/pith-number/L6VR5NL2EKXULRGKACQ7QB4FLM/events.json","paper":"https://pith.science/paper/L6VR5NL2"},"agent_actions":{"view_html":"https://pith.science/pith/L6VR5NL2EKXULRGKACQ7QB4FLM","download_json":"https://pith.science/pith/L6VR5NL2EKXULRGKACQ7QB4FLM.json","view_paper":"https://pith.science/paper/L6VR5NL2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.11271&json=true","fetch_graph":"https://pith.science/api/pith-number/L6VR5NL2EKXULRGKACQ7QB4FLM/graph.json","fetch_events":"https://pith.science/api/pith-number/L6VR5NL2EKXULRGKACQ7QB4FLM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L6VR5NL2EKXULRGKACQ7QB4FLM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L6VR5NL2EKXULRGKACQ7QB4FLM/action/storage_attestation","attest_author":"https://pith.science/pith/L6VR5NL2EKXULRGKACQ7QB4FLM/action/author_attestation","sign_citation":"https://pith.science/pith/L6VR5NL2EKXULRGKACQ7QB4FLM/action/citation_signature","submit_replication":"https://pith.science/pith/L6VR5NL2EKXULRGKACQ7QB4FLM/action/replication_record"}},"created_at":"2026-05-18T00:08:00.379815+00:00","updated_at":"2026-05-18T00:08:00.379815+00:00"}