{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SSYOIGWIJ6NA6ECJAZXYYEVVH7","short_pith_number":"pith:SSYOIGWI","schema_version":"1.0","canonical_sha256":"94b0e41ac84f9a0f1049066f8c12b53ff1827b773e858916b03a193352c2b6c1","source":{"kind":"arxiv","id":"2605.29684","version":1},"attestation_state":"computed","paper":{"title":"Kernel Renormalization in Bayesian Deep Neural Networks: the Equivalent Wishart Ansatz in the Proportional Regime","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Vezzani, Christian Keup, Paolo Baglioni, Pietro Rotondo, Raffaella Burioni, Rosalba Pacelli, Vincenzo Zimbardo","submitted_at":"2026-05-28T09:49:54Z","abstract_excerpt":"The scaling limit where both the size of the training set $P$ and the width $N$ of a deep neural network grow at the same rate, the so-called proportional-width regime, has been intensely studied for shallow, single-hidden-layer networks. However, extending these non-perturbative results from shallow architectures to deep non-linear networks has proven very challenging. Here we present an effective approximate approach to predict the generalization performance of Bayesian multi-layer perceptrons (MLPs) of fixed depth $L$ on arbitrary high-dimensional data. We propose an equivalent Wishart Ansa"},"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":"2605.29684","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T09:49:54Z","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"title_canon_sha256":"11c329ec055449bb29976a6cbbef326210417d998aa2cfecdf3e5b626612fb3e","abstract_canon_sha256":"e71928a9035b26503c2495249854431b6f9ada005a80e90b004bda35827dced9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:55.444713Z","signature_b64":"s0mwgIn10LvwbZRwSMqU+N5UarAmzAl2T8L5b7RZUsulacg6RzVwHjI3kS9T5ZdhOa48/bFja6QkMgnnODpfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94b0e41ac84f9a0f1049066f8c12b53ff1827b773e858916b03a193352c2b6c1","last_reissued_at":"2026-05-29T01:05:55.444242Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:55.444242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kernel Renormalization in Bayesian Deep Neural Networks: the Equivalent Wishart Ansatz in the Proportional Regime","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Vezzani, Christian Keup, Paolo Baglioni, Pietro Rotondo, Raffaella Burioni, Rosalba Pacelli, Vincenzo Zimbardo","submitted_at":"2026-05-28T09:49:54Z","abstract_excerpt":"The scaling limit where both the size of the training set $P$ and the width $N$ of a deep neural network grow at the same rate, the so-called proportional-width regime, has been intensely studied for shallow, single-hidden-layer networks. However, extending these non-perturbative results from shallow architectures to deep non-linear networks has proven very challenging. Here we present an effective approximate approach to predict the generalization performance of Bayesian multi-layer perceptrons (MLPs) of fixed depth $L$ on arbitrary high-dimensional data. We propose an equivalent Wishart Ansa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29684","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.29684/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":"2605.29684","created_at":"2026-05-29T01:05:55.444306+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29684v1","created_at":"2026-05-29T01:05:55.444306+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29684","created_at":"2026-05-29T01:05:55.444306+00:00"},{"alias_kind":"pith_short_12","alias_value":"SSYOIGWIJ6NA","created_at":"2026-05-29T01:05:55.444306+00:00"},{"alias_kind":"pith_short_16","alias_value":"SSYOIGWIJ6NA6ECJ","created_at":"2026-05-29T01:05:55.444306+00:00"},{"alias_kind":"pith_short_8","alias_value":"SSYOIGWI","created_at":"2026-05-29T01:05:55.444306+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SSYOIGWIJ6NA6ECJAZXYYEVVH7","json":"https://pith.science/pith/SSYOIGWIJ6NA6ECJAZXYYEVVH7.json","graph_json":"https://pith.science/api/pith-number/SSYOIGWIJ6NA6ECJAZXYYEVVH7/graph.json","events_json":"https://pith.science/api/pith-number/SSYOIGWIJ6NA6ECJAZXYYEVVH7/events.json","paper":"https://pith.science/paper/SSYOIGWI"},"agent_actions":{"view_html":"https://pith.science/pith/SSYOIGWIJ6NA6ECJAZXYYEVVH7","download_json":"https://pith.science/pith/SSYOIGWIJ6NA6ECJAZXYYEVVH7.json","view_paper":"https://pith.science/paper/SSYOIGWI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29684&json=true","fetch_graph":"https://pith.science/api/pith-number/SSYOIGWIJ6NA6ECJAZXYYEVVH7/graph.json","fetch_events":"https://pith.science/api/pith-number/SSYOIGWIJ6NA6ECJAZXYYEVVH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SSYOIGWIJ6NA6ECJAZXYYEVVH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SSYOIGWIJ6NA6ECJAZXYYEVVH7/action/storage_attestation","attest_author":"https://pith.science/pith/SSYOIGWIJ6NA6ECJAZXYYEVVH7/action/author_attestation","sign_citation":"https://pith.science/pith/SSYOIGWIJ6NA6ECJAZXYYEVVH7/action/citation_signature","submit_replication":"https://pith.science/pith/SSYOIGWIJ6NA6ECJAZXYYEVVH7/action/replication_record"}},"created_at":"2026-05-29T01:05:55.444306+00:00","updated_at":"2026-05-29T01:05:55.444306+00:00"}