{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:WP623CUQBHJ3HBZMVG2AMUDF27","short_pith_number":"pith:WP623CUQ","canonical_record":{"source":{"id":"1907.00865","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-01T15:25:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d2d56589386b9f258c479ffd11f1c336985f22b41f8f9d0c6434f53ae36eb008","abstract_canon_sha256":"7c9550d4997041cdddd6351b7a222d3f1e2011941fd162d83131e0bc958c9ed0"},"schema_version":"1.0"},"canonical_sha256":"b3fdad8a9009d3b3872ca9b4065065d7ea70a03d0c7c5498c8c1689c322dd225","source":{"kind":"arxiv","id":"1907.00865","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.00865","created_at":"2026-07-05T02:44:30Z"},{"alias_kind":"arxiv_version","alias_value":"1907.00865v4","created_at":"2026-07-05T02:44:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.00865","created_at":"2026-07-05T02:44:30Z"},{"alias_kind":"pith_short_12","alias_value":"WP623CUQBHJ3","created_at":"2026-07-05T02:44:30Z"},{"alias_kind":"pith_short_16","alias_value":"WP623CUQBHJ3HBZM","created_at":"2026-07-05T02:44:30Z"},{"alias_kind":"pith_short_8","alias_value":"WP623CUQ","created_at":"2026-07-05T02:44:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:WP623CUQBHJ3HBZMVG2AMUDF27","target":"record","payload":{"canonical_record":{"source":{"id":"1907.00865","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-01T15:25:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d2d56589386b9f258c479ffd11f1c336985f22b41f8f9d0c6434f53ae36eb008","abstract_canon_sha256":"7c9550d4997041cdddd6351b7a222d3f1e2011941fd162d83131e0bc958c9ed0"},"schema_version":"1.0"},"canonical_sha256":"b3fdad8a9009d3b3872ca9b4065065d7ea70a03d0c7c5498c8c1689c322dd225","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:30.910592Z","signature_b64":"5oSRxW41kDrs8OuE7IquyWlGNTNP0usj9gP0aq84Bp3hVKksDT+6v5+ZeWZbpfrK2eqwW0zt04xqfG2UJkS+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3fdad8a9009d3b3872ca9b4065065d7ea70a03d0c7c5498c8c1689c322dd225","last_reissued_at":"2026-07-05T02:44:30.910114Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:30.910114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.00865","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:44:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2JwCmpCww38RPMdfK7nNj5EUsEQKeV7ZHPw5rn9RAhg4i1lQ1u4JswIn3srZcQ+dBrVc1FP+uqKYEz6iTR4rDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T12:31:27.576773Z"},"content_sha256":"96a1a4f05f6f3ed30ca83f271f202b2f1eccaf067132409d0fdbc119634115a1","schema_version":"1.0","event_id":"sha256:96a1a4f05f6f3ed30ca83f271f202b2f1eccaf067132409d0fdbc119634115a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:WP623CUQBHJ3HBZMVG2AMUDF27","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Michael Osborne, Sebastian Farquhar, Yarin Gal","submitted_at":"2019-07-01T15:25:50Z","abstract_excerpt":"We propose Radial Bayesian Neural Networks (BNNs): a variational approximate posterior for BNNs which scales well to large models while maintaining a distribution over weight-space with full support. Other scalable Bayesian deep learning methods, like MC dropout or deep ensembles, have discrete support-they assign zero probability to almost all of the weight-space. Unlike these discrete support methods, Radial BNNs' full support makes them suitable for use as a prior for sequential inference. In addition, they solve the conceptual challenges with the a priori implausibility of weight distribut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.00865","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1907.00865/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T02:44:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pd/iZF+Bd5hvoK5nWx1d22eLj15bpNJaePHXy8VdHgYdq5cvdOy0m3DgiMqvULuyEpFW2KFo0uj5j7fzP2wFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T12:31:27.577146Z"},"content_sha256":"22dc48e1fee4c98a17d94300fe453081ac7ae62c01b0fc9e343270a7c31ca215","schema_version":"1.0","event_id":"sha256:22dc48e1fee4c98a17d94300fe453081ac7ae62c01b0fc9e343270a7c31ca215"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WP623CUQBHJ3HBZMVG2AMUDF27/bundle.json","state_url":"https://pith.science/pith/WP623CUQBHJ3HBZMVG2AMUDF27/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WP623CUQBHJ3HBZMVG2AMUDF27/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":"2026-07-14T12:31:27Z","links":{"resolver":"https://pith.science/pith/WP623CUQBHJ3HBZMVG2AMUDF27","bundle":"https://pith.science/pith/WP623CUQBHJ3HBZMVG2AMUDF27/bundle.json","state":"https://pith.science/pith/WP623CUQBHJ3HBZMVG2AMUDF27/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WP623CUQBHJ3HBZMVG2AMUDF27/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WP623CUQBHJ3HBZMVG2AMUDF27","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":"7c9550d4997041cdddd6351b7a222d3f1e2011941fd162d83131e0bc958c9ed0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-01T15:25:50Z","title_canon_sha256":"d2d56589386b9f258c479ffd11f1c336985f22b41f8f9d0c6434f53ae36eb008"},"schema_version":"1.0","source":{"id":"1907.00865","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.00865","created_at":"2026-07-05T02:44:30Z"},{"alias_kind":"arxiv_version","alias_value":"1907.00865v4","created_at":"2026-07-05T02:44:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.00865","created_at":"2026-07-05T02:44:30Z"},{"alias_kind":"pith_short_12","alias_value":"WP623CUQBHJ3","created_at":"2026-07-05T02:44:30Z"},{"alias_kind":"pith_short_16","alias_value":"WP623CUQBHJ3HBZM","created_at":"2026-07-05T02:44:30Z"},{"alias_kind":"pith_short_8","alias_value":"WP623CUQ","created_at":"2026-07-05T02:44:30Z"}],"graph_snapshots":[{"event_id":"sha256:22dc48e1fee4c98a17d94300fe453081ac7ae62c01b0fc9e343270a7c31ca215","target":"graph","created_at":"2026-07-05T02:44:30Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1907.00865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Radial Bayesian Neural Networks (BNNs): a variational approximate posterior for BNNs which scales well to large models while maintaining a distribution over weight-space with full support. Other scalable Bayesian deep learning methods, like MC dropout or deep ensembles, have discrete support-they assign zero probability to almost all of the weight-space. Unlike these discrete support methods, Radial BNNs' full support makes them suitable for use as a prior for sequential inference. In addition, they solve the conceptual challenges with the a priori implausibility of weight distribut","authors_text":"Michael Osborne, Sebastian Farquhar, Yarin Gal","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-01T15:25:50Z","title":"Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.00865","kind":"arxiv","version":4},"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":"sha256:96a1a4f05f6f3ed30ca83f271f202b2f1eccaf067132409d0fdbc119634115a1","target":"record","created_at":"2026-07-05T02:44:30Z","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":"7c9550d4997041cdddd6351b7a222d3f1e2011941fd162d83131e0bc958c9ed0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-01T15:25:50Z","title_canon_sha256":"d2d56589386b9f258c479ffd11f1c336985f22b41f8f9d0c6434f53ae36eb008"},"schema_version":"1.0","source":{"id":"1907.00865","kind":"arxiv","version":4}},"canonical_sha256":"b3fdad8a9009d3b3872ca9b4065065d7ea70a03d0c7c5498c8c1689c322dd225","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3fdad8a9009d3b3872ca9b4065065d7ea70a03d0c7c5498c8c1689c322dd225","first_computed_at":"2026-07-05T02:44:30.910114Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:44:30.910114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5oSRxW41kDrs8OuE7IquyWlGNTNP0usj9gP0aq84Bp3hVKksDT+6v5+ZeWZbpfrK2eqwW0zt04xqfG2UJkS+BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:44:30.910592Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.00865","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96a1a4f05f6f3ed30ca83f271f202b2f1eccaf067132409d0fdbc119634115a1","sha256:22dc48e1fee4c98a17d94300fe453081ac7ae62c01b0fc9e343270a7c31ca215"],"state_sha256":"66b7f4c6080d25798687a04d8ee3431f1c352a8f182e080fd27e32e7df164fad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ekQVUjzUKW53fqZWQQZ20vQ3fDiGlwvHcc3mOhjlhKuLp59EDqKDeK86EyJLVEHPNKAz21EXA1VZxW6IJOowCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T12:31:27.579730Z","bundle_sha256":"b74761c71eb2c7dd9f20f7f3d616e29c853620f8b34a5aefca2799ad3af1318e"}}