{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:GRTKHP2RA4DOR2MKHUBIEREMBK","short_pith_number":"pith:GRTKHP2R","canonical_record":{"source":{"id":"1711.01297","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-03T18:49:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8a02812fc30fe66d75a9b8fd50366e2435fe2a287418bffe35f742af437ecbbc","abstract_canon_sha256":"6791cc7dca2e1f0d15ea1ff68d783338c24ab791c8fef2f9caa40962f0c17e17"},"schema_version":"1.0"},"canonical_sha256":"3466a3bf510706e8e98a3d0282448c0aa1fea6f09987a294cc780c3812e14d48","source":{"kind":"arxiv","id":"1711.01297","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.01297","created_at":"2026-05-18T00:14:59Z"},{"alias_kind":"arxiv_version","alias_value":"1711.01297v2","created_at":"2026-05-18T00:14:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.01297","created_at":"2026-05-18T00:14:59Z"},{"alias_kind":"pith_short_12","alias_value":"GRTKHP2RA4DO","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GRTKHP2RA4DOR2MK","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GRTKHP2R","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:GRTKHP2RA4DOR2MKHUBIEREMBK","target":"record","payload":{"canonical_record":{"source":{"id":"1711.01297","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-03T18:49:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8a02812fc30fe66d75a9b8fd50366e2435fe2a287418bffe35f742af437ecbbc","abstract_canon_sha256":"6791cc7dca2e1f0d15ea1ff68d783338c24ab791c8fef2f9caa40962f0c17e17"},"schema_version":"1.0"},"canonical_sha256":"3466a3bf510706e8e98a3d0282448c0aa1fea6f09987a294cc780c3812e14d48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:59.803251Z","signature_b64":"J0FwAFxHoP1grQabDAJL5LNBxCUWSQC/BVQFeRx/jFewi7MN1dswQtvaYchry2ErTaZPGpmGOqwQwoHpMkC7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3466a3bf510706e8e98a3d0282448c0aa1fea6f09987a294cc780c3812e14d48","last_reissued_at":"2026-05-18T00:14:59.802600Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:59.802600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.01297","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":"2026-05-18T00:14:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fks2h155DNCwjHJ+eyORiQLZcrRlHud1tfskjP8G5ZQ4QjYA56Tsy3PyJoz8Ithjuslz3a1bd49KicT+Z3n4CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T01:13:52.335432Z"},"content_sha256":"3d0aedea1dd47efb4c299c2c147042df52bfca7fde4830718ef56d7098edec88","schema_version":"1.0","event_id":"sha256:3d0aedea1dd47efb4c299c2c147042df52bfca7fde4830718ef56d7098edec88"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:GRTKHP2RA4DOR2MKHUBIEREMBK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Implicit Weight Uncertainty in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrew Brock, Ben Glocker, Martin Rajchl, Matthew C.H. Lee, Nick Pawlowski","submitted_at":"2017-11-03T18:49:04Z","abstract_excerpt":"Modern neural networks tend to be overconfident on unseen, noisy or incorrectly labelled data and do not produce meaningful uncertainty measures. Bayesian deep learning aims to address this shortcoming with variational approximations (such as Bayes by Backprop or Multiplicative Normalising Flows). However, current approaches have limitations regarding flexibility and scalability. We introduce Bayes by Hypernet (BbH), a new method of variational approximation that interprets hypernetworks as implicit distributions. It naturally uses neural networks to model arbitrarily complex distributions and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.01297","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":"2026-05-18T00:14:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"knpR1Qw2vu9awX5a6f8wExnZd2PoXGUKYHjfg+x+NTiTLVYcOByTp6e1C16ViIrviS4kBq0UO3ItiePmlLd5CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T01:13:52.336221Z"},"content_sha256":"995d84148d224e937df08cebeb034fa472de31732b6ee30e3b1acc2011be3c32","schema_version":"1.0","event_id":"sha256:995d84148d224e937df08cebeb034fa472de31732b6ee30e3b1acc2011be3c32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GRTKHP2RA4DOR2MKHUBIEREMBK/bundle.json","state_url":"https://pith.science/pith/GRTKHP2RA4DOR2MKHUBIEREMBK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GRTKHP2RA4DOR2MKHUBIEREMBK/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":"2026-05-30T01:13:52Z","links":{"resolver":"https://pith.science/pith/GRTKHP2RA4DOR2MKHUBIEREMBK","bundle":"https://pith.science/pith/GRTKHP2RA4DOR2MKHUBIEREMBK/bundle.json","state":"https://pith.science/pith/GRTKHP2RA4DOR2MKHUBIEREMBK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GRTKHP2RA4DOR2MKHUBIEREMBK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:GRTKHP2RA4DOR2MKHUBIEREMBK","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":"6791cc7dca2e1f0d15ea1ff68d783338c24ab791c8fef2f9caa40962f0c17e17","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-03T18:49:04Z","title_canon_sha256":"8a02812fc30fe66d75a9b8fd50366e2435fe2a287418bffe35f742af437ecbbc"},"schema_version":"1.0","source":{"id":"1711.01297","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.01297","created_at":"2026-05-18T00:14:59Z"},{"alias_kind":"arxiv_version","alias_value":"1711.01297v2","created_at":"2026-05-18T00:14:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.01297","created_at":"2026-05-18T00:14:59Z"},{"alias_kind":"pith_short_12","alias_value":"GRTKHP2RA4DO","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GRTKHP2RA4DOR2MK","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GRTKHP2R","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:995d84148d224e937df08cebeb034fa472de31732b6ee30e3b1acc2011be3c32","target":"graph","created_at":"2026-05-18T00:14:59Z","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":"Modern neural networks tend to be overconfident on unseen, noisy or incorrectly labelled data and do not produce meaningful uncertainty measures. Bayesian deep learning aims to address this shortcoming with variational approximations (such as Bayes by Backprop or Multiplicative Normalising Flows). However, current approaches have limitations regarding flexibility and scalability. We introduce Bayes by Hypernet (BbH), a new method of variational approximation that interprets hypernetworks as implicit distributions. It naturally uses neural networks to model arbitrarily complex distributions and","authors_text":"Andrew Brock, Ben Glocker, Martin Rajchl, Matthew C.H. Lee, Nick Pawlowski","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-03T18:49:04Z","title":"Implicit Weight Uncertainty in Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.01297","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":"sha256:3d0aedea1dd47efb4c299c2c147042df52bfca7fde4830718ef56d7098edec88","target":"record","created_at":"2026-05-18T00:14:59Z","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":"6791cc7dca2e1f0d15ea1ff68d783338c24ab791c8fef2f9caa40962f0c17e17","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-03T18:49:04Z","title_canon_sha256":"8a02812fc30fe66d75a9b8fd50366e2435fe2a287418bffe35f742af437ecbbc"},"schema_version":"1.0","source":{"id":"1711.01297","kind":"arxiv","version":2}},"canonical_sha256":"3466a3bf510706e8e98a3d0282448c0aa1fea6f09987a294cc780c3812e14d48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3466a3bf510706e8e98a3d0282448c0aa1fea6f09987a294cc780c3812e14d48","first_computed_at":"2026-05-18T00:14:59.802600Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:59.802600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J0FwAFxHoP1grQabDAJL5LNBxCUWSQC/BVQFeRx/jFewi7MN1dswQtvaYchry2ErTaZPGpmGOqwQwoHpMkC7CA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:59.803251Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.01297","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d0aedea1dd47efb4c299c2c147042df52bfca7fde4830718ef56d7098edec88","sha256:995d84148d224e937df08cebeb034fa472de31732b6ee30e3b1acc2011be3c32"],"state_sha256":"bd7d2fb55fe6cfbaa27221e1b929f1d0dabfbc753e3faf02e300ee7d2a925d26"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rpZF0d4du6sWNhRB3xidcKy71xnEc7Mef7egqZpHCwsBfsFl6zyMamBI5NLCQPV9n/Wc99jM/NotBMSKXvhtDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T01:13:52.339635Z","bundle_sha256":"5e53f053b9db8ce3ae2698dbca5dec7afc110d9c6bc186ac5e052927c96def3d"}}