{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:O4UH33JEFGOBUZSSWC5VO7KCCR","short_pith_number":"pith:O4UH33JE","schema_version":"1.0","canonical_sha256":"77287ded24299c1a6652b0bb577d4214709a91d04079143e0109ae4dcfee80e9","source":{"kind":"arxiv","id":"1903.05779","version":1},"attestation_state":"computed","paper":{"title":"Functional Variational Bayesian Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guodong Zhang, Jiaxin Shi, Roger Grosse, Shengyang Sun","submitted_at":"2019-03-14T01:05:24Z","abstract_excerpt":"Variational Bayesian neural networks (BNNs) perform variational inference over weights, but it is difficult to specify meaningful priors and approximate posteriors in a high-dimensional weight space. We introduce functional variational Bayesian neural networks (fBNNs), which maximize an Evidence Lower BOund (ELBO) defined directly on stochastic processes, i.e. distributions over functions. We prove that the KL divergence between stochastic processes equals the supremum of marginal KL divergences over all finite sets of inputs. Based on this, we introduce a practical training objective which ap"},"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":"1903.05779","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-14T01:05:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"59708fa3b60a57a0f08288335f6038206bd319278082c33e51a00879cdb178e5","abstract_canon_sha256":"78261302ebb1031dfac41741bb01de14b35b3067b30ce6a4a3b1d5415f31473a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:16.253874Z","signature_b64":"W3A8KURyIh2LM4Uji/TDfD6suvY8/BgJBFGfyzvoq2DrbMmY6ndMfdd/Y9ycA+PJMv9e/sW8E+pPZl7WhfViBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77287ded24299c1a6652b0bb577d4214709a91d04079143e0109ae4dcfee80e9","last_reissued_at":"2026-05-17T23:51:16.253262Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:16.253262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Functional Variational Bayesian Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guodong Zhang, Jiaxin Shi, Roger Grosse, Shengyang Sun","submitted_at":"2019-03-14T01:05:24Z","abstract_excerpt":"Variational Bayesian neural networks (BNNs) perform variational inference over weights, but it is difficult to specify meaningful priors and approximate posteriors in a high-dimensional weight space. We introduce functional variational Bayesian neural networks (fBNNs), which maximize an Evidence Lower BOund (ELBO) defined directly on stochastic processes, i.e. distributions over functions. We prove that the KL divergence between stochastic processes equals the supremum of marginal KL divergences over all finite sets of inputs. Based on this, we introduce a practical training objective which ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.05779","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":""},"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":"1903.05779","created_at":"2026-05-17T23:51:16.253360+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.05779v1","created_at":"2026-05-17T23:51:16.253360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.05779","created_at":"2026-05-17T23:51:16.253360+00:00"},{"alias_kind":"pith_short_12","alias_value":"O4UH33JEFGOB","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"O4UH33JEFGOBUZSS","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"O4UH33JE","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09686","citing_title":"Quality of Uncertainty Quantification for Bayesian Neural Network Inference","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10378","citing_title":"Uncertainty in Physics and AI: Taxonomy, Quantification, and Validation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O4UH33JEFGOBUZSSWC5VO7KCCR","json":"https://pith.science/pith/O4UH33JEFGOBUZSSWC5VO7KCCR.json","graph_json":"https://pith.science/api/pith-number/O4UH33JEFGOBUZSSWC5VO7KCCR/graph.json","events_json":"https://pith.science/api/pith-number/O4UH33JEFGOBUZSSWC5VO7KCCR/events.json","paper":"https://pith.science/paper/O4UH33JE"},"agent_actions":{"view_html":"https://pith.science/pith/O4UH33JEFGOBUZSSWC5VO7KCCR","download_json":"https://pith.science/pith/O4UH33JEFGOBUZSSWC5VO7KCCR.json","view_paper":"https://pith.science/paper/O4UH33JE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.05779&json=true","fetch_graph":"https://pith.science/api/pith-number/O4UH33JEFGOBUZSSWC5VO7KCCR/graph.json","fetch_events":"https://pith.science/api/pith-number/O4UH33JEFGOBUZSSWC5VO7KCCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O4UH33JEFGOBUZSSWC5VO7KCCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O4UH33JEFGOBUZSSWC5VO7KCCR/action/storage_attestation","attest_author":"https://pith.science/pith/O4UH33JEFGOBUZSSWC5VO7KCCR/action/author_attestation","sign_citation":"https://pith.science/pith/O4UH33JEFGOBUZSSWC5VO7KCCR/action/citation_signature","submit_replication":"https://pith.science/pith/O4UH33JEFGOBUZSSWC5VO7KCCR/action/replication_record"}},"created_at":"2026-05-17T23:51:16.253360+00:00","updated_at":"2026-05-17T23:51:16.253360+00:00"}