{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BQ5HSWBHOSNSNQNUTREBA4FOJT","short_pith_number":"pith:BQ5HSWBH","schema_version":"1.0","canonical_sha256":"0c3a795827749b26c1b49c481070ae4cfd33e09fad0bd255139679242c9b9599","source":{"kind":"arxiv","id":"2507.22095","version":5},"attestation_state":"computed","paper":{"title":"Posterior Bayesian Neural Networks with Dependent Weights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Giovanni Franzina, Giovanni Luca Torrisi, Nicola Apollonio","submitted_at":"2025-07-29T15:54:34Z","abstract_excerpt":"We consider fully connected and feedforward deep neural networks with dependent and possibly heavy-tailed weights, as introduced in [26], to address limitations of the standard Gaussian prior. It has been proved in [26] that, as the number of nodes in the hidden layers grows large, according to a sequential and ordered limit, the law of the output converges weakly to a Gaussian mixture. In this paper, we study the neural network through the lens of the posterior distribution with a Gaussian likelihood. If the random covariance matrix of the infinite-width limit is positive definite under the p"},"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":"2507.22095","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-07-29T15:54:34Z","cross_cats_sorted":["cs.LG","math.PR"],"title_canon_sha256":"45dbba604ee275d8a599c55772780062952c1d71f66c4b2be899f7a24435d2eb","abstract_canon_sha256":"1298e623965d0590302c68840ad7c7d71cd949379d3b310c0df1e37a01455472"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:34.952918Z","signature_b64":"ZKaIApz9oXs/z/lPEChLp1CjJOsJ8Iw6Ke31haWgDbty5znCdvNvUt3MZVFkcYJ3Ax+xkQdFQqEL7bTlz3TZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c3a795827749b26c1b49c481070ae4cfd33e09fad0bd255139679242c9b9599","last_reissued_at":"2026-05-18T03:09:34.952444Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:34.952444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Posterior Bayesian Neural Networks with Dependent Weights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Giovanni Franzina, Giovanni Luca Torrisi, Nicola Apollonio","submitted_at":"2025-07-29T15:54:34Z","abstract_excerpt":"We consider fully connected and feedforward deep neural networks with dependent and possibly heavy-tailed weights, as introduced in [26], to address limitations of the standard Gaussian prior. It has been proved in [26] that, as the number of nodes in the hidden layers grows large, according to a sequential and ordered limit, the law of the output converges weakly to a Gaussian mixture. In this paper, we study the neural network through the lens of the posterior distribution with a Gaussian likelihood. If the random covariance matrix of the infinite-width limit is positive definite under the p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22095","kind":"arxiv","version":5},"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":"2507.22095","created_at":"2026-05-18T03:09:34.952516+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22095v5","created_at":"2026-05-18T03:09:34.952516+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22095","created_at":"2026-05-18T03:09:34.952516+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQ5HSWBHOSNS","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQ5HSWBHOSNSNQNU","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQ5HSWBH","created_at":"2026-05-18T12:33:37.589309+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/BQ5HSWBHOSNSNQNUTREBA4FOJT","json":"https://pith.science/pith/BQ5HSWBHOSNSNQNUTREBA4FOJT.json","graph_json":"https://pith.science/api/pith-number/BQ5HSWBHOSNSNQNUTREBA4FOJT/graph.json","events_json":"https://pith.science/api/pith-number/BQ5HSWBHOSNSNQNUTREBA4FOJT/events.json","paper":"https://pith.science/paper/BQ5HSWBH"},"agent_actions":{"view_html":"https://pith.science/pith/BQ5HSWBHOSNSNQNUTREBA4FOJT","download_json":"https://pith.science/pith/BQ5HSWBHOSNSNQNUTREBA4FOJT.json","view_paper":"https://pith.science/paper/BQ5HSWBH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22095&json=true","fetch_graph":"https://pith.science/api/pith-number/BQ5HSWBHOSNSNQNUTREBA4FOJT/graph.json","fetch_events":"https://pith.science/api/pith-number/BQ5HSWBHOSNSNQNUTREBA4FOJT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQ5HSWBHOSNSNQNUTREBA4FOJT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQ5HSWBHOSNSNQNUTREBA4FOJT/action/storage_attestation","attest_author":"https://pith.science/pith/BQ5HSWBHOSNSNQNUTREBA4FOJT/action/author_attestation","sign_citation":"https://pith.science/pith/BQ5HSWBHOSNSNQNUTREBA4FOJT/action/citation_signature","submit_replication":"https://pith.science/pith/BQ5HSWBHOSNSNQNUTREBA4FOJT/action/replication_record"}},"created_at":"2026-05-18T03:09:34.952516+00:00","updated_at":"2026-05-18T03:09:34.952516+00:00"}