{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:GTXZVSDA4KNZ4OZNEVSJUKPDNF","short_pith_number":"pith:GTXZVSDA","canonical_record":{"source":{"id":"1810.03958","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T13:30:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"55c230351854af256e803dd228fa0dc26cd04d33b002c696cef49c452378f159","abstract_canon_sha256":"87b52a6b21c863e5e841cd38fe7f49bfc541a7d9bc7580e6bfed5bd71e14a03d"},"schema_version":"1.0"},"canonical_sha256":"34ef9ac860e29b9e3b2d25649a29e3695a4bd1a3d0deb91a86147a1fc04b8b8c","source":{"kind":"arxiv","id":"1810.03958","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03958","created_at":"2026-05-17T23:51:52Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03958v2","created_at":"2026-05-17T23:51:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03958","created_at":"2026-05-17T23:51:52Z"},{"alias_kind":"pith_short_12","alias_value":"GTXZVSDA4KNZ","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GTXZVSDA4KNZ4OZN","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GTXZVSDA","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:GTXZVSDA4KNZ4OZNEVSJUKPDNF","target":"record","payload":{"canonical_record":{"source":{"id":"1810.03958","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T13:30:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"55c230351854af256e803dd228fa0dc26cd04d33b002c696cef49c452378f159","abstract_canon_sha256":"87b52a6b21c863e5e841cd38fe7f49bfc541a7d9bc7580e6bfed5bd71e14a03d"},"schema_version":"1.0"},"canonical_sha256":"34ef9ac860e29b9e3b2d25649a29e3695a4bd1a3d0deb91a86147a1fc04b8b8c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:52.449834Z","signature_b64":"Fyn4LFPXaxPs7KVVExx8AOlPiGiH99PeGfAg8obZAREA+8aXQIR3rW8UlZfHT46AnMT6C6hMOo//xiW/O3UtAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34ef9ac860e29b9e3b2d25649a29e3695a4bd1a3d0deb91a86147a1fc04b8b8c","last_reissued_at":"2026-05-17T23:51:52.449178Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:52.449178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.03958","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yt0+FfWfn6+8PbXavX0yWOKjx/Q5+reqHRH07UZ+vGTFIbzjSbWGCKqrOnH7yyLGYdsLegih/0R5qxlWjMGCAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T21:51:09.755714Z"},"content_sha256":"132c75a46b66e050efad9ad6a5d85d1245935984b4af21ca014be6c554a59409","schema_version":"1.0","event_id":"sha256:132c75a46b66e050efad9ad6a5d85d1245935984b4af21ca014be6c554a59409"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:GTXZVSDA4KNZ4OZNEVSJUKPDNF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deterministic Variational Inference for Robust Bayesian Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander L. Gaunt, Anqi Wu, Edward Meeds, Jos\\'e Miguel Hern\\'andez-Lobato, Richard E. Turner, Sebastian Nowozin","submitted_at":"2018-10-09T13:30:58Z","abstract_excerpt":"Bayesian neural networks (BNNs) hold great promise as a flexible and principled solution to deal with uncertainty when learning from finite data. Among approaches to realize probabilistic inference in deep neural networks, variational Bayes (VB) is theoretically grounded, generally applicable, and computationally efficient. With wide recognition of potential advantages, why is it that variational Bayes has seen very limited practical use for BNNs in real applications? We argue that variational inference in neural networks is fragile: successful implementations require careful initialization an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03958","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"71G08zCT2RA2zoteFBcyYBjp6iQ487hQgMKPilDBbEKeyxE8sCGOpgl4EueG9fM6199qbQlfyhvcgy0ka/GsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T21:51:09.756411Z"},"content_sha256":"28cab139f5ce70c0628b2da7d474280b9731e39b6f3822cb9a7f7b43ff558351","schema_version":"1.0","event_id":"sha256:28cab139f5ce70c0628b2da7d474280b9731e39b6f3822cb9a7f7b43ff558351"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GTXZVSDA4KNZ4OZNEVSJUKPDNF/bundle.json","state_url":"https://pith.science/pith/GTXZVSDA4KNZ4OZNEVSJUKPDNF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GTXZVSDA4KNZ4OZNEVSJUKPDNF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T21:51:09Z","links":{"resolver":"https://pith.science/pith/GTXZVSDA4KNZ4OZNEVSJUKPDNF","bundle":"https://pith.science/pith/GTXZVSDA4KNZ4OZNEVSJUKPDNF/bundle.json","state":"https://pith.science/pith/GTXZVSDA4KNZ4OZNEVSJUKPDNF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GTXZVSDA4KNZ4OZNEVSJUKPDNF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:GTXZVSDA4KNZ4OZNEVSJUKPDNF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"87b52a6b21c863e5e841cd38fe7f49bfc541a7d9bc7580e6bfed5bd71e14a03d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T13:30:58Z","title_canon_sha256":"55c230351854af256e803dd228fa0dc26cd04d33b002c696cef49c452378f159"},"schema_version":"1.0","source":{"id":"1810.03958","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03958","created_at":"2026-05-17T23:51:52Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03958v2","created_at":"2026-05-17T23:51:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03958","created_at":"2026-05-17T23:51:52Z"},{"alias_kind":"pith_short_12","alias_value":"GTXZVSDA4KNZ","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GTXZVSDA4KNZ4OZN","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GTXZVSDA","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:28cab139f5ce70c0628b2da7d474280b9731e39b6f3822cb9a7f7b43ff558351","target":"graph","created_at":"2026-05-17T23:51:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Bayesian neural networks (BNNs) hold great promise as a flexible and principled solution to deal with uncertainty when learning from finite data. Among approaches to realize probabilistic inference in deep neural networks, variational Bayes (VB) is theoretically grounded, generally applicable, and computationally efficient. With wide recognition of potential advantages, why is it that variational Bayes has seen very limited practical use for BNNs in real applications? We argue that variational inference in neural networks is fragile: successful implementations require careful initialization an","authors_text":"Alexander L. Gaunt, Anqi Wu, Edward Meeds, Jos\\'e Miguel Hern\\'andez-Lobato, Richard E. Turner, Sebastian Nowozin","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T13:30:58Z","title":"Deterministic Variational Inference for Robust Bayesian Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03958","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:132c75a46b66e050efad9ad6a5d85d1245935984b4af21ca014be6c554a59409","target":"record","created_at":"2026-05-17T23:51:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"87b52a6b21c863e5e841cd38fe7f49bfc541a7d9bc7580e6bfed5bd71e14a03d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T13:30:58Z","title_canon_sha256":"55c230351854af256e803dd228fa0dc26cd04d33b002c696cef49c452378f159"},"schema_version":"1.0","source":{"id":"1810.03958","kind":"arxiv","version":2}},"canonical_sha256":"34ef9ac860e29b9e3b2d25649a29e3695a4bd1a3d0deb91a86147a1fc04b8b8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34ef9ac860e29b9e3b2d25649a29e3695a4bd1a3d0deb91a86147a1fc04b8b8c","first_computed_at":"2026-05-17T23:51:52.449178Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:52.449178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fyn4LFPXaxPs7KVVExx8AOlPiGiH99PeGfAg8obZAREA+8aXQIR3rW8UlZfHT46AnMT6C6hMOo//xiW/O3UtAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:52.449834Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.03958","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:132c75a46b66e050efad9ad6a5d85d1245935984b4af21ca014be6c554a59409","sha256:28cab139f5ce70c0628b2da7d474280b9731e39b6f3822cb9a7f7b43ff558351"],"state_sha256":"b45e4cd3353a200487fac20eab40230b95fd1a731691edddfc8031bd040c0105"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eLM4ba//b5ft9aCFlVa8a0S31U3ZYP4FaOrqLcyu5UrvNa2rMjd0t86WECojLlcoMr9EWflvsGmVtpEEcunDDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T21:51:09.759899Z","bundle_sha256":"b30a7455f78ad56595fd611cbf433d7896aecf81a4115adaab4356db56ff887b"}}