{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2ZQFQTSQNJVLBZSAOX3Q7AZ43L","short_pith_number":"pith:2ZQFQTSQ","schema_version":"1.0","canonical_sha256":"d660584e506a6ab0e64075f70f833cdad1b001b5322e26a7154cd8673287864c","source":{"kind":"arxiv","id":"2603.06023","version":2},"attestation_state":"computed","paper":{"title":"Large deviation principles for convolutional Bayesian neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.PR","authors_text":"Federico Bassetti, Lucia Ladelli, Vassili De Palma","submitted_at":"2026-03-06T08:18:15Z","abstract_excerpt":"While suitably scaled CNNs with Gaussian initialization are known to converge to Gaussian processes as the number of channels diverges, little is known beyond this Gaussian limit. We establish a large deviation principle (LDP) for convolutional neural networks in the infinite-channel regime.\n  We consider a broad class of multidimensional CNN architectures characterized by general receptive fields encoded through a patch-extractor function satisfying mild structural assumptions. Our main result establishes a large deviation principle (LDP) for the sequence of conditional covariance matrices un"},"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":"2603.06023","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.PR","submitted_at":"2026-03-06T08:18:15Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b46f2ab517a4ca2179261837b88bfe0db76318a87c4fee8aad02ee2978c6fe28","abstract_canon_sha256":"2f9934c42d68b60de9cc43e8963b13d7e456dfb7aedf946a17f6e024d2b8c9f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:23.274243Z","signature_b64":"8rd7TjXNHvFd5pofEPPP7AHTXOCsikUXzqjiLaUZY1Ns0Elvz8X3viqA2RiIYrG/o9XgkUshH5R8qAsPM4N1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d660584e506a6ab0e64075f70f833cdad1b001b5322e26a7154cd8673287864c","last_reissued_at":"2026-06-09T02:07:23.273198Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:23.273198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large deviation principles for convolutional Bayesian neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.PR","authors_text":"Federico Bassetti, Lucia Ladelli, Vassili De Palma","submitted_at":"2026-03-06T08:18:15Z","abstract_excerpt":"While suitably scaled CNNs with Gaussian initialization are known to converge to Gaussian processes as the number of channels diverges, little is known beyond this Gaussian limit. We establish a large deviation principle (LDP) for convolutional neural networks in the infinite-channel regime.\n  We consider a broad class of multidimensional CNN architectures characterized by general receptive fields encoded through a patch-extractor function satisfying mild structural assumptions. Our main result establishes a large deviation principle (LDP) for the sequence of conditional covariance matrices un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.06023","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.06023/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":"2603.06023","created_at":"2026-06-09T02:07:23.273364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.06023v2","created_at":"2026-06-09T02:07:23.273364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.06023","created_at":"2026-06-09T02:07:23.273364+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZQFQTSQNJVL","created_at":"2026-06-09T02:07:23.273364+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZQFQTSQNJVLBZSA","created_at":"2026-06-09T02:07:23.273364+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZQFQTSQ","created_at":"2026-06-09T02:07:23.273364+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/2ZQFQTSQNJVLBZSAOX3Q7AZ43L","json":"https://pith.science/pith/2ZQFQTSQNJVLBZSAOX3Q7AZ43L.json","graph_json":"https://pith.science/api/pith-number/2ZQFQTSQNJVLBZSAOX3Q7AZ43L/graph.json","events_json":"https://pith.science/api/pith-number/2ZQFQTSQNJVLBZSAOX3Q7AZ43L/events.json","paper":"https://pith.science/paper/2ZQFQTSQ"},"agent_actions":{"view_html":"https://pith.science/pith/2ZQFQTSQNJVLBZSAOX3Q7AZ43L","download_json":"https://pith.science/pith/2ZQFQTSQNJVLBZSAOX3Q7AZ43L.json","view_paper":"https://pith.science/paper/2ZQFQTSQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.06023&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZQFQTSQNJVLBZSAOX3Q7AZ43L/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZQFQTSQNJVLBZSAOX3Q7AZ43L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZQFQTSQNJVLBZSAOX3Q7AZ43L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZQFQTSQNJVLBZSAOX3Q7AZ43L/action/storage_attestation","attest_author":"https://pith.science/pith/2ZQFQTSQNJVLBZSAOX3Q7AZ43L/action/author_attestation","sign_citation":"https://pith.science/pith/2ZQFQTSQNJVLBZSAOX3Q7AZ43L/action/citation_signature","submit_replication":"https://pith.science/pith/2ZQFQTSQNJVLBZSAOX3Q7AZ43L/action/replication_record"}},"created_at":"2026-06-09T02:07:23.273364+00:00","updated_at":"2026-06-09T02:07:23.273364+00:00"}