{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:4XDBCHRXFXTYAQGOOIEC2ETQNJ","short_pith_number":"pith:4XDBCHRX","canonical_record":{"source":{"id":"1905.09453","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-23T03:58:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ca9d45af8681c8d0db005a9698e8779f417711afe0e04302c702c59496039002","abstract_canon_sha256":"ec63e96c865d0fee5dbaa56f2c330e6fea33db5e41f323e98c5f566bca4b7905"},"schema_version":"1.0"},"canonical_sha256":"e5c6111e372de78040ce72082d12706a7f068910392838d3e1272ac429b06c13","source":{"kind":"arxiv","id":"1905.09453","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.09453","created_at":"2026-05-17T23:45:16Z"},{"alias_kind":"arxiv_version","alias_value":"1905.09453v1","created_at":"2026-05-17T23:45:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09453","created_at":"2026-05-17T23:45:16Z"},{"alias_kind":"pith_short_12","alias_value":"4XDBCHRXFXTY","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4XDBCHRXFXTYAQGO","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4XDBCHRX","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:4XDBCHRXFXTYAQGOOIEC2ETQNJ","target":"record","payload":{"canonical_record":{"source":{"id":"1905.09453","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-23T03:58:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ca9d45af8681c8d0db005a9698e8779f417711afe0e04302c702c59496039002","abstract_canon_sha256":"ec63e96c865d0fee5dbaa56f2c330e6fea33db5e41f323e98c5f566bca4b7905"},"schema_version":"1.0"},"canonical_sha256":"e5c6111e372de78040ce72082d12706a7f068910392838d3e1272ac429b06c13","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:16.988106Z","signature_b64":"vRxSOBqCn+yM/LgMdYboJD/PlHXnHF03HAQ7ooh1c8kA0pIj5udripcKVcwusZTB6hKc8eLFLEf+oQn+sRGJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5c6111e372de78040ce72082d12706a7f068910392838d3e1272ac429b06c13","last_reissued_at":"2026-05-17T23:45:16.987463Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:16.987463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.09453","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":"2026-05-17T23:45:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9zGxhN8PWXVs7qG0zIulwCfsiqq9X/IY9DC7BeWpHeoZt2QJqAfMVTAsHrUXOnMbjUJaB0tiaKcdlfG3ZmsiDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:32:22.159567Z"},"content_sha256":"49cabf1f0cd357ef2af81de70ba10d198199ddf511cf0761d9d0ada881b76578","schema_version":"1.0","event_id":"sha256:49cabf1f0cd357ef2af81de70ba10d198199ddf511cf0761d9d0ada881b76578"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:4XDBCHRXFXTYAQGOOIEC2ETQNJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ensemble Model Patching: A Parameter-Efficient Variational Bayesian Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Williams-King, Hod Lipson, Oscar Chang, Yuling Yao","submitted_at":"2019-05-23T03:58:59Z","abstract_excerpt":"Two main obstacles preventing the widespread adoption of variational Bayesian neural networks are the high parameter overhead that makes them infeasible on large networks, and the difficulty of implementation, which can be thought of as \"programming overhead.\" MC dropout [Gal and Ghahramani, 2016] is popular because it sidesteps these obstacles. Nevertheless, dropout is often harmful to model performance when used in networks with batch normalization layers [Li et al., 2018], which are an indispensable part of modern neural networks. We construct a general variational family for ensemble-based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09453","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":"2026-05-17T23:45:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uqaRnbPyn6EPaHSAZCtJP+SDZCEbR0FxrDShO3dDaSSqg++YgkIVYZEwInTtr9uZifryJ8FYvMom1sNCMudFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:32:22.160056Z"},"content_sha256":"59580b798cef42c466ceb731f2777eb1919b97224f233457a7a0bbce63a90ca0","schema_version":"1.0","event_id":"sha256:59580b798cef42c466ceb731f2777eb1919b97224f233457a7a0bbce63a90ca0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4XDBCHRXFXTYAQGOOIEC2ETQNJ/bundle.json","state_url":"https://pith.science/pith/4XDBCHRXFXTYAQGOOIEC2ETQNJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4XDBCHRXFXTYAQGOOIEC2ETQNJ/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":"2026-05-26T08:32:22Z","links":{"resolver":"https://pith.science/pith/4XDBCHRXFXTYAQGOOIEC2ETQNJ","bundle":"https://pith.science/pith/4XDBCHRXFXTYAQGOOIEC2ETQNJ/bundle.json","state":"https://pith.science/pith/4XDBCHRXFXTYAQGOOIEC2ETQNJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4XDBCHRXFXTYAQGOOIEC2ETQNJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4XDBCHRXFXTYAQGOOIEC2ETQNJ","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":"ec63e96c865d0fee5dbaa56f2c330e6fea33db5e41f323e98c5f566bca4b7905","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-23T03:58:59Z","title_canon_sha256":"ca9d45af8681c8d0db005a9698e8779f417711afe0e04302c702c59496039002"},"schema_version":"1.0","source":{"id":"1905.09453","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.09453","created_at":"2026-05-17T23:45:16Z"},{"alias_kind":"arxiv_version","alias_value":"1905.09453v1","created_at":"2026-05-17T23:45:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09453","created_at":"2026-05-17T23:45:16Z"},{"alias_kind":"pith_short_12","alias_value":"4XDBCHRXFXTY","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4XDBCHRXFXTYAQGO","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4XDBCHRX","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:59580b798cef42c466ceb731f2777eb1919b97224f233457a7a0bbce63a90ca0","target":"graph","created_at":"2026-05-17T23:45:16Z","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":"Two main obstacles preventing the widespread adoption of variational Bayesian neural networks are the high parameter overhead that makes them infeasible on large networks, and the difficulty of implementation, which can be thought of as \"programming overhead.\" MC dropout [Gal and Ghahramani, 2016] is popular because it sidesteps these obstacles. Nevertheless, dropout is often harmful to model performance when used in networks with batch normalization layers [Li et al., 2018], which are an indispensable part of modern neural networks. We construct a general variational family for ensemble-based","authors_text":"David Williams-King, Hod Lipson, Oscar Chang, Yuling Yao","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-23T03:58:59Z","title":"Ensemble Model Patching: A Parameter-Efficient Variational Bayesian Neural Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09453","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":"sha256:49cabf1f0cd357ef2af81de70ba10d198199ddf511cf0761d9d0ada881b76578","target":"record","created_at":"2026-05-17T23:45:16Z","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":"ec63e96c865d0fee5dbaa56f2c330e6fea33db5e41f323e98c5f566bca4b7905","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-23T03:58:59Z","title_canon_sha256":"ca9d45af8681c8d0db005a9698e8779f417711afe0e04302c702c59496039002"},"schema_version":"1.0","source":{"id":"1905.09453","kind":"arxiv","version":1}},"canonical_sha256":"e5c6111e372de78040ce72082d12706a7f068910392838d3e1272ac429b06c13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5c6111e372de78040ce72082d12706a7f068910392838d3e1272ac429b06c13","first_computed_at":"2026-05-17T23:45:16.987463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:16.987463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vRxSOBqCn+yM/LgMdYboJD/PlHXnHF03HAQ7ooh1c8kA0pIj5udripcKVcwusZTB6hKc8eLFLEf+oQn+sRGJCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:16.988106Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.09453","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49cabf1f0cd357ef2af81de70ba10d198199ddf511cf0761d9d0ada881b76578","sha256:59580b798cef42c466ceb731f2777eb1919b97224f233457a7a0bbce63a90ca0"],"state_sha256":"5bd7848bc16be0cd439893e3a70067359ef81bae84fa775c846a03a1c367c4b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p/b4iaPZd47LyjPOpbE+s0hh7quFpoleopX83S39QRE+9kIcCTjwApq/ZA2HW9nTZyfx54nC5E9WG8tvYDGVBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T08:32:22.163534Z","bundle_sha256":"3cdadac54cbadea362b3b9409b1e01cd0d9532ba04619d2136625043e40b96e9"}}