{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5OP5H2DPTLK35NNEZ3NHDQV3E4","short_pith_number":"pith:5OP5H2DP","schema_version":"1.0","canonical_sha256":"eb9fd3e86f9ad5beb5a4ceda71c2bb2716c3d14d779f9ba37275034c035e070d","source":{"kind":"arxiv","id":"2206.08065","version":3},"attestation_state":"computed","paper":{"title":"Large-width asymptotics for ReLU neural networks with $\\alpha$-Stable initializations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Sandra Fortini, Stefano Favaro, Stefano Peluchetti","submitted_at":"2022-06-16T10:28:03Z","abstract_excerpt":"There is a recent and growing literature on large-width asymptotic properties of Gaussian neural networks (NNs), namely NNs whose weights are initialized as Gaussian distributions. Two popular problems are: i) the study of the large-width distributions of NNs, which characterizes the infinitely wide limit of a rescaled NN in terms of a Gaussian stochastic process; ii) the study of the large-width training dynamics of NNs, which characterizes the infinitely wide dynamics in terms of a deterministic kernel, referred to as the neural tangent kernel (NTK), and shows that, for a sufficiently large "},"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":"2206.08065","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-16T10:28:03Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"27acfb3b6b5932442c5b1f8944cea14faa94a6e0114ad2ae380893773e042a7b","abstract_canon_sha256":"ac2a6926c7c6d72577fda5ac829b034051655eeec218b51a7976072b7010e412"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:29.923007Z","signature_b64":"Jw7hWZDlxnP1qNof90MLhKoaeHu7kdqLdqZYiBvcy250DDRrJwq1K/zMAwqDzzomB3rcGyPzp/R+d62BeKayDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb9fd3e86f9ad5beb5a4ceda71c2bb2716c3d14d779f9ba37275034c035e070d","last_reissued_at":"2026-07-05T05:30:29.922570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:29.922570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-width asymptotics for ReLU neural networks with $\\alpha$-Stable initializations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Sandra Fortini, Stefano Favaro, Stefano Peluchetti","submitted_at":"2022-06-16T10:28:03Z","abstract_excerpt":"There is a recent and growing literature on large-width asymptotic properties of Gaussian neural networks (NNs), namely NNs whose weights are initialized as Gaussian distributions. Two popular problems are: i) the study of the large-width distributions of NNs, which characterizes the infinitely wide limit of a rescaled NN in terms of a Gaussian stochastic process; ii) the study of the large-width training dynamics of NNs, which characterizes the infinitely wide dynamics in terms of a deterministic kernel, referred to as the neural tangent kernel (NTK), and shows that, for a sufficiently large "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08065","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/2206.08065/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":"2206.08065","created_at":"2026-07-05T05:30:29.922656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.08065v3","created_at":"2026-07-05T05:30:29.922656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08065","created_at":"2026-07-05T05:30:29.922656+00:00"},{"alias_kind":"pith_short_12","alias_value":"5OP5H2DPTLK3","created_at":"2026-07-05T05:30:29.922656+00:00"},{"alias_kind":"pith_short_16","alias_value":"5OP5H2DPTLK35NNE","created_at":"2026-07-05T05:30:29.922656+00:00"},{"alias_kind":"pith_short_8","alias_value":"5OP5H2DP","created_at":"2026-07-05T05:30:29.922656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15267","citing_title":"Proportional infinite-width infinite-depth limit for deep linear neural networks","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5OP5H2DPTLK35NNEZ3NHDQV3E4","json":"https://pith.science/pith/5OP5H2DPTLK35NNEZ3NHDQV3E4.json","graph_json":"https://pith.science/api/pith-number/5OP5H2DPTLK35NNEZ3NHDQV3E4/graph.json","events_json":"https://pith.science/api/pith-number/5OP5H2DPTLK35NNEZ3NHDQV3E4/events.json","paper":"https://pith.science/paper/5OP5H2DP"},"agent_actions":{"view_html":"https://pith.science/pith/5OP5H2DPTLK35NNEZ3NHDQV3E4","download_json":"https://pith.science/pith/5OP5H2DPTLK35NNEZ3NHDQV3E4.json","view_paper":"https://pith.science/paper/5OP5H2DP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.08065&json=true","fetch_graph":"https://pith.science/api/pith-number/5OP5H2DPTLK35NNEZ3NHDQV3E4/graph.json","fetch_events":"https://pith.science/api/pith-number/5OP5H2DPTLK35NNEZ3NHDQV3E4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5OP5H2DPTLK35NNEZ3NHDQV3E4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5OP5H2DPTLK35NNEZ3NHDQV3E4/action/storage_attestation","attest_author":"https://pith.science/pith/5OP5H2DPTLK35NNEZ3NHDQV3E4/action/author_attestation","sign_citation":"https://pith.science/pith/5OP5H2DPTLK35NNEZ3NHDQV3E4/action/citation_signature","submit_replication":"https://pith.science/pith/5OP5H2DPTLK35NNEZ3NHDQV3E4/action/replication_record"}},"created_at":"2026-07-05T05:30:29.922656+00:00","updated_at":"2026-07-05T05:30:29.922656+00:00"}