{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:JYZR6TYRCZ43GTEVJAVIAFCYHZ","short_pith_number":"pith:JYZR6TYR","canonical_record":{"source":{"id":"1904.01334","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-02T11:06:50Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"4a3239569f4ff1bc974d6265eb7f62044be9249f414afa80a9f63a601b95eea2","abstract_canon_sha256":"c15aa1fa02ae6250c41f0ff97dc98f3d584e89db6abb7960f349b06904bdd548"},"schema_version":"1.0"},"canonical_sha256":"4e331f4f111679b34c95482a8014583e7541f3739aab51839f0c4f8925475473","source":{"kind":"arxiv","id":"1904.01334","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.01334","created_at":"2026-05-17T23:49:35Z"},{"alias_kind":"arxiv_version","alias_value":"1904.01334v1","created_at":"2026-05-17T23:49:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01334","created_at":"2026-05-17T23:49:35Z"},{"alias_kind":"pith_short_12","alias_value":"JYZR6TYRCZ43","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"JYZR6TYRCZ43GTEV","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"JYZR6TYR","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:JYZR6TYRCZ43GTEVJAVIAFCYHZ","target":"record","payload":{"canonical_record":{"source":{"id":"1904.01334","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-02T11:06:50Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"4a3239569f4ff1bc974d6265eb7f62044be9249f414afa80a9f63a601b95eea2","abstract_canon_sha256":"c15aa1fa02ae6250c41f0ff97dc98f3d584e89db6abb7960f349b06904bdd548"},"schema_version":"1.0"},"canonical_sha256":"4e331f4f111679b34c95482a8014583e7541f3739aab51839f0c4f8925475473","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:35.051050Z","signature_b64":"fhh3rz0KA+t02MwNG+HACjfhhE6G3PiDWdBVdcqaGyd/Lwd/YaTGJ/VtlS6uahPrVpaq+dZcakq1C3yZPHIwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e331f4f111679b34c95482a8014583e7541f3739aab51839f0c4f8925475473","last_reissued_at":"2026-05-17T23:49:35.050416Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:35.050416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.01334","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:49:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mi+YUYFbo5ey0SapSdSA49PE+jnwm1/IWm/s+8tWe1Q9bUhQZA4pSdxOqxHU0Ug4hHZx31dSVT57yRftgME5BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T08:15:32.230659Z"},"content_sha256":"47f08d59002848cb6df5e2dea71ec41d5186557bfac0b3e2c57dda6a64adb98a","schema_version":"1.0","event_id":"sha256:47f08d59002848cb6df5e2dea71ec41d5186557bfac0b3e2c57dda6a64adb98a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:JYZR6TYRCZ43GTEVJAVIAFCYHZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Correlated Parameters to Accurately Measure Uncertainty in Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"J\\\"urgen Pilz, Konstantin Posch","submitted_at":"2019-04-02T11:06:50Z","abstract_excerpt":"In this article a novel approach for training deep neural networks using Bayesian techniques is presented. The Bayesian methodology allows for an easy evaluation of model uncertainty and additionally is robust to overfitting. These are commonly the two main problems classical, i.e. non-Bayesian, architectures have to struggle with. The proposed approach applies variational inference in order to approximate the intractable posterior distribution. In particular, the variational distribution is defined as product of multiple multivariate normal distributions with tridiagonal covariance matrices. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01334","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:49:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WpkX0jyrgYVH/37kymN9o9+Mr1CeeGDkgpBD6ui9jjbZMIFg2/nLd2y96bgJORfmIbGNc1o6hdnykE7I/oquDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T08:15:32.231006Z"},"content_sha256":"059c5bffe5cbc8be1978d34b24b04f46f5f4c466dd9624627acdc06b32895b7f","schema_version":"1.0","event_id":"sha256:059c5bffe5cbc8be1978d34b24b04f46f5f4c466dd9624627acdc06b32895b7f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JYZR6TYRCZ43GTEVJAVIAFCYHZ/bundle.json","state_url":"https://pith.science/pith/JYZR6TYRCZ43GTEVJAVIAFCYHZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JYZR6TYRCZ43GTEVJAVIAFCYHZ/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":"2026-06-24T08:15:32Z","links":{"resolver":"https://pith.science/pith/JYZR6TYRCZ43GTEVJAVIAFCYHZ","bundle":"https://pith.science/pith/JYZR6TYRCZ43GTEVJAVIAFCYHZ/bundle.json","state":"https://pith.science/pith/JYZR6TYRCZ43GTEVJAVIAFCYHZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JYZR6TYRCZ43GTEVJAVIAFCYHZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JYZR6TYRCZ43GTEVJAVIAFCYHZ","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":"c15aa1fa02ae6250c41f0ff97dc98f3d584e89db6abb7960f349b06904bdd548","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-02T11:06:50Z","title_canon_sha256":"4a3239569f4ff1bc974d6265eb7f62044be9249f414afa80a9f63a601b95eea2"},"schema_version":"1.0","source":{"id":"1904.01334","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.01334","created_at":"2026-05-17T23:49:35Z"},{"alias_kind":"arxiv_version","alias_value":"1904.01334v1","created_at":"2026-05-17T23:49:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01334","created_at":"2026-05-17T23:49:35Z"},{"alias_kind":"pith_short_12","alias_value":"JYZR6TYRCZ43","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"JYZR6TYRCZ43GTEV","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"JYZR6TYR","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:059c5bffe5cbc8be1978d34b24b04f46f5f4c466dd9624627acdc06b32895b7f","target":"graph","created_at":"2026-05-17T23:49:35Z","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":"In this article a novel approach for training deep neural networks using Bayesian techniques is presented. The Bayesian methodology allows for an easy evaluation of model uncertainty and additionally is robust to overfitting. These are commonly the two main problems classical, i.e. non-Bayesian, architectures have to struggle with. The proposed approach applies variational inference in order to approximate the intractable posterior distribution. In particular, the variational distribution is defined as product of multiple multivariate normal distributions with tridiagonal covariance matrices. ","authors_text":"J\\\"urgen Pilz, Konstantin Posch","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-02T11:06:50Z","title":"Correlated Parameters to Accurately Measure Uncertainty in Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01334","kind":"arxiv","version":1},"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":"sha256:47f08d59002848cb6df5e2dea71ec41d5186557bfac0b3e2c57dda6a64adb98a","target":"record","created_at":"2026-05-17T23:49:35Z","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":"c15aa1fa02ae6250c41f0ff97dc98f3d584e89db6abb7960f349b06904bdd548","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-02T11:06:50Z","title_canon_sha256":"4a3239569f4ff1bc974d6265eb7f62044be9249f414afa80a9f63a601b95eea2"},"schema_version":"1.0","source":{"id":"1904.01334","kind":"arxiv","version":1}},"canonical_sha256":"4e331f4f111679b34c95482a8014583e7541f3739aab51839f0c4f8925475473","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e331f4f111679b34c95482a8014583e7541f3739aab51839f0c4f8925475473","first_computed_at":"2026-05-17T23:49:35.050416Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:35.050416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fhh3rz0KA+t02MwNG+HACjfhhE6G3PiDWdBVdcqaGyd/Lwd/YaTGJ/VtlS6uahPrVpaq+dZcakq1C3yZPHIwCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:35.051050Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.01334","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47f08d59002848cb6df5e2dea71ec41d5186557bfac0b3e2c57dda6a64adb98a","sha256:059c5bffe5cbc8be1978d34b24b04f46f5f4c466dd9624627acdc06b32895b7f"],"state_sha256":"f821676a03702c2461855323ffc5b0bfbfc5cd0fe622b0303d48f94b66aecf86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hnMjZYEow/3VzLvSuXHnBn90hh7s2XFBJmfPdHRx8PvsI5i/fHLlAw1euMJSDMbMsNQ63aaoOGlHOIpDi8lKCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-24T08:15:32.232997Z","bundle_sha256":"d595652185b100db414878e57c97ac3707ebc7ed2560b52097dbeca449e8fca4"}}