{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:W2SMJSL4YSDRXVY65TV7IBEK2B","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":"678c18c35e84d7a30fc6453f09d3d0e4f7457512cc2a7610a3089db001550cf8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-26T20:04:15Z","title_canon_sha256":"305aec41aedcecff3e8f57c431f05b1ce920c9b82c173bb1eeec2bc0f67b3371"},"schema_version":"1.0","source":{"id":"1902.10189","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.10189","created_at":"2026-05-17T23:51:46Z"},{"alias_kind":"arxiv_version","alias_value":"1902.10189v2","created_at":"2026-05-17T23:51:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10189","created_at":"2026-05-17T23:51:46Z"},{"alias_kind":"pith_short_12","alias_value":"W2SMJSL4YSDR","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"W2SMJSL4YSDRXVY6","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"W2SMJSL4","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:b7299fb06dcc6cded07df2ef765aa6bd892a9990432a0bc313c0842a30a74dfc","target":"graph","created_at":"2026-05-17T23:51:46Z","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":"We present a novel approach for training deep neural networks in a Bayesian way. Classical, i.e. non-Bayesian, deep learning has two major drawbacks both originating from the fact that network parameters are considered to be deterministic. First, model uncertainty cannot be measured thus limiting the use of deep learning in many fields of application and second, training of deep neural networks is often hampered by overfitting. The proposed approach uses variational inference to approximate the intractable a posteriori distribution on basis of a normal prior. The variational density is designe","authors_text":"Jan Steinbrener, J\\\"urgen Pilz, Konstantin Posch","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-26T20:04:15Z","title":"Variational Inference to Measure Model Uncertainty in Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10189","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":"sha256:1d2f060c08d8230d241b44f4c6b555bfc8257cd7b71d33161c8fc5e79192f4b0","target":"record","created_at":"2026-05-17T23:51:46Z","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":"678c18c35e84d7a30fc6453f09d3d0e4f7457512cc2a7610a3089db001550cf8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-26T20:04:15Z","title_canon_sha256":"305aec41aedcecff3e8f57c431f05b1ce920c9b82c173bb1eeec2bc0f67b3371"},"schema_version":"1.0","source":{"id":"1902.10189","kind":"arxiv","version":2}},"canonical_sha256":"b6a4c4c97cc4871bd71eecebf4048ad06a0baa3bb2c5694998764d74d971121b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6a4c4c97cc4871bd71eecebf4048ad06a0baa3bb2c5694998764d74d971121b","first_computed_at":"2026-05-17T23:51:46.536012Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:46.536012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oJ1XJ6NfXNJ8ZY5MVgFqp06cKnjLz4AUdHT1sPESzUnMoYAKpW9oZOS5snkJSuYLXhmEeZavCsxlvpopty2CBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:46.536713Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.10189","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d2f060c08d8230d241b44f4c6b555bfc8257cd7b71d33161c8fc5e79192f4b0","sha256:b7299fb06dcc6cded07df2ef765aa6bd892a9990432a0bc313c0842a30a74dfc"],"state_sha256":"c097651c049a908518d19ca202fae0ddc78a89583deafe71fc25d81f1cadd92e"}