{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:44VVXTC4RU4RJOG6JW5QXYV6KA","short_pith_number":"pith:44VVXTC4","schema_version":"1.0","canonical_sha256":"e72b5bcc5c8d3914b8de4dbb0be2be501aa708402842736b296aff7618ca539b","source":{"kind":"arxiv","id":"1810.05546","version":5},"attestation_state":"computed","paper":{"title":"Uncertainty in Neural Networks: Approximately Bayesian Ensembling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexandra Brintrup, Andy Neely, Felix Leibfried, Mohamed Zaki, Tim Pearce","submitted_at":"2018-10-12T14:26:34Z","abstract_excerpt":"Understanding the uncertainty of a neural network's (NN) predictions is essential for many purposes. The Bayesian framework provides a principled approach to this, however applying it to NNs is challenging due to large numbers of parameters and data. Ensembling NNs provides an easily implementable, scalable method for uncertainty quantification, however, it has been criticised for not being Bayesian. This work proposes one modification to the usual process that we argue does result in approximate Bayesian inference; regularising parameters about values drawn from a distribution which can be se"},"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":"1810.05546","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-12T14:26:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c61f7592744fe12d480de4f29b26209b88c2c1dd02ca26984d795b045e7c3f40","abstract_canon_sha256":"82c5fc70b2d73ed44092e223bca4d28ecd0e57b57e2fe4b1ed54c268be91a85e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:52.862159Z","signature_b64":"9dVVIrZ2GIpZrVsX0tjislL3Bmz9Ms5DRqVyRtyhmXxIxqhzvxZl0Ya174IqTDXl2OFU37utpDdqkzLB6Dx/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e72b5bcc5c8d3914b8de4dbb0be2be501aa708402842736b296aff7618ca539b","last_reissued_at":"2026-07-05T00:43:52.861686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:52.861686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty in Neural Networks: Approximately Bayesian Ensembling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexandra Brintrup, Andy Neely, Felix Leibfried, Mohamed Zaki, Tim Pearce","submitted_at":"2018-10-12T14:26:34Z","abstract_excerpt":"Understanding the uncertainty of a neural network's (NN) predictions is essential for many purposes. The Bayesian framework provides a principled approach to this, however applying it to NNs is challenging due to large numbers of parameters and data. Ensembling NNs provides an easily implementable, scalable method for uncertainty quantification, however, it has been criticised for not being Bayesian. This work proposes one modification to the usual process that we argue does result in approximate Bayesian inference; regularising parameters about values drawn from a distribution which can be se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.05546","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1810.05546/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":"1810.05546","created_at":"2026-07-05T00:43:52.861743+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.05546v5","created_at":"2026-07-05T00:43:52.861743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.05546","created_at":"2026-07-05T00:43:52.861743+00:00"},{"alias_kind":"pith_short_12","alias_value":"44VVXTC4RU4R","created_at":"2026-07-05T00:43:52.861743+00:00"},{"alias_kind":"pith_short_16","alias_value":"44VVXTC4RU4RJOG6","created_at":"2026-07-05T00:43:52.861743+00:00"},{"alias_kind":"pith_short_8","alias_value":"44VVXTC4","created_at":"2026-07-05T00:43:52.861743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1906.09686","citing_title":"Quality of Uncertainty Quantification for Bayesian Neural Network Inference","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/44VVXTC4RU4RJOG6JW5QXYV6KA","json":"https://pith.science/pith/44VVXTC4RU4RJOG6JW5QXYV6KA.json","graph_json":"https://pith.science/api/pith-number/44VVXTC4RU4RJOG6JW5QXYV6KA/graph.json","events_json":"https://pith.science/api/pith-number/44VVXTC4RU4RJOG6JW5QXYV6KA/events.json","paper":"https://pith.science/paper/44VVXTC4"},"agent_actions":{"view_html":"https://pith.science/pith/44VVXTC4RU4RJOG6JW5QXYV6KA","download_json":"https://pith.science/pith/44VVXTC4RU4RJOG6JW5QXYV6KA.json","view_paper":"https://pith.science/paper/44VVXTC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.05546&json=true","fetch_graph":"https://pith.science/api/pith-number/44VVXTC4RU4RJOG6JW5QXYV6KA/graph.json","fetch_events":"https://pith.science/api/pith-number/44VVXTC4RU4RJOG6JW5QXYV6KA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/44VVXTC4RU4RJOG6JW5QXYV6KA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/44VVXTC4RU4RJOG6JW5QXYV6KA/action/storage_attestation","attest_author":"https://pith.science/pith/44VVXTC4RU4RJOG6JW5QXYV6KA/action/author_attestation","sign_citation":"https://pith.science/pith/44VVXTC4RU4RJOG6JW5QXYV6KA/action/citation_signature","submit_replication":"https://pith.science/pith/44VVXTC4RU4RJOG6JW5QXYV6KA/action/replication_record"}},"created_at":"2026-07-05T00:43:52.861743+00:00","updated_at":"2026-07-05T00:43:52.861743+00:00"}