{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:EM53U57MRWHN6OZCVNXXDVDQ76","short_pith_number":"pith:EM53U57M","schema_version":"1.0","canonical_sha256":"233bba77ec8d8edf3b22ab6f71d470ff9052cc33d1de14f36e61016638978026","source":{"kind":"arxiv","id":"1906.11537","version":1},"attestation_state":"computed","paper":{"title":"'In-Between' Uncertainty in Bayesian Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrew Y. K. Foong, Jos\\'e Miguel Hern\\'andez-Lobato, Richard E. Turner, Yingzhen Li","submitted_at":"2019-06-27T10:25:14Z","abstract_excerpt":"We describe a limitation in the expressiveness of the predictive uncertainty estimate given by mean-field variational inference (MFVI), a popular approximate inference method for Bayesian neural networks. In particular, MFVI fails to give calibrated uncertainty estimates in between separated regions of observations. This can lead to catastrophically overconfident predictions when testing on out-of-distribution data. Avoiding such overconfidence is critical for active learning, Bayesian optimisation and out-of-distribution robustness. We instead find that a classical technique, the linearised L"},"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":"1906.11537","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-06-27T10:25:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d87322b2d7e89d18cdb0c0a5c92fd90cdf53b5389abe92a275b7562d401c6553","abstract_canon_sha256":"cf1a303e666319761861e0f04c31ee5ac93f5b398a5dd8ce8e5aeeba8d2e53d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:04.528540Z","signature_b64":"TQ4m7h2XL/ESPB355WnHekXyGq+3fInsqJ9slnH75A7SyJUVzbGQg0vlEpHwmEENaDgZuHaWCIfusELsUg+VAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"233bba77ec8d8edf3b22ab6f71d470ff9052cc33d1de14f36e61016638978026","last_reissued_at":"2026-05-17T23:42:04.527923Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:04.527923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"'In-Between' Uncertainty in Bayesian Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrew Y. K. Foong, Jos\\'e Miguel Hern\\'andez-Lobato, Richard E. Turner, Yingzhen Li","submitted_at":"2019-06-27T10:25:14Z","abstract_excerpt":"We describe a limitation in the expressiveness of the predictive uncertainty estimate given by mean-field variational inference (MFVI), a popular approximate inference method for Bayesian neural networks. In particular, MFVI fails to give calibrated uncertainty estimates in between separated regions of observations. This can lead to catastrophically overconfident predictions when testing on out-of-distribution data. Avoiding such overconfidence is critical for active learning, Bayesian optimisation and out-of-distribution robustness. We instead find that a classical technique, the linearised L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.11537","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":"1906.11537","created_at":"2026-05-17T23:42:04.528012+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.11537v1","created_at":"2026-05-17T23:42:04.528012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.11537","created_at":"2026-05-17T23:42:04.528012+00:00"},{"alias_kind":"pith_short_12","alias_value":"EM53U57MRWHN","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"EM53U57MRWHN6OZC","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"EM53U57M","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02345","citing_title":"Low Rank Based Subspace Inference for the Laplace Approximation of Bayesian Neural Networks","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09075","citing_title":"Optimality of Sub-network Laplace Approximations: New Results and Methods","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EM53U57MRWHN6OZCVNXXDVDQ76","json":"https://pith.science/pith/EM53U57MRWHN6OZCVNXXDVDQ76.json","graph_json":"https://pith.science/api/pith-number/EM53U57MRWHN6OZCVNXXDVDQ76/graph.json","events_json":"https://pith.science/api/pith-number/EM53U57MRWHN6OZCVNXXDVDQ76/events.json","paper":"https://pith.science/paper/EM53U57M"},"agent_actions":{"view_html":"https://pith.science/pith/EM53U57MRWHN6OZCVNXXDVDQ76","download_json":"https://pith.science/pith/EM53U57MRWHN6OZCVNXXDVDQ76.json","view_paper":"https://pith.science/paper/EM53U57M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.11537&json=true","fetch_graph":"https://pith.science/api/pith-number/EM53U57MRWHN6OZCVNXXDVDQ76/graph.json","fetch_events":"https://pith.science/api/pith-number/EM53U57MRWHN6OZCVNXXDVDQ76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EM53U57MRWHN6OZCVNXXDVDQ76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EM53U57MRWHN6OZCVNXXDVDQ76/action/storage_attestation","attest_author":"https://pith.science/pith/EM53U57MRWHN6OZCVNXXDVDQ76/action/author_attestation","sign_citation":"https://pith.science/pith/EM53U57MRWHN6OZCVNXXDVDQ76/action/citation_signature","submit_replication":"https://pith.science/pith/EM53U57MRWHN6OZCVNXXDVDQ76/action/replication_record"}},"created_at":"2026-05-17T23:42:04.528012+00:00","updated_at":"2026-05-17T23:42:04.528012+00:00"}