{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:HSZICJWQ6FEJ5BZZGQLKDJ6K5G","short_pith_number":"pith:HSZICJWQ","canonical_record":{"source":{"id":"1502.05336","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-02-18T18:45:17Z","cross_cats_sorted":[],"title_canon_sha256":"489c81a7b91abf6befbefed56bc516b730457c9e5e8f3bcc2a7dfde20829fddd","abstract_canon_sha256":"15ed332b58754ce355c68a02c21c970a56d92647b02eb50b098cfe2642d68017"},"schema_version":"1.0"},"canonical_sha256":"3cb28126d0f1489e87393416a1a7cae9953b584f636394ff341a78ee02773000","source":{"kind":"arxiv","id":"1502.05336","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.05336","created_at":"2026-05-18T01:36:51Z"},{"alias_kind":"arxiv_version","alias_value":"1502.05336v2","created_at":"2026-05-18T01:36:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.05336","created_at":"2026-05-18T01:36:51Z"},{"alias_kind":"pith_short_12","alias_value":"HSZICJWQ6FEJ","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"HSZICJWQ6FEJ5BZZ","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"HSZICJWQ","created_at":"2026-05-18T12:29:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:HSZICJWQ6FEJ5BZZGQLKDJ6K5G","target":"record","payload":{"canonical_record":{"source":{"id":"1502.05336","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-02-18T18:45:17Z","cross_cats_sorted":[],"title_canon_sha256":"489c81a7b91abf6befbefed56bc516b730457c9e5e8f3bcc2a7dfde20829fddd","abstract_canon_sha256":"15ed332b58754ce355c68a02c21c970a56d92647b02eb50b098cfe2642d68017"},"schema_version":"1.0"},"canonical_sha256":"3cb28126d0f1489e87393416a1a7cae9953b584f636394ff341a78ee02773000","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:36:51.355092Z","signature_b64":"9jZc2EjkZUbPIrMWcMpChy5K0ExQtHoQlGKnLhmCU9lOr9lIG6ifNSMtaDahFtzeg/JN6EjmsLvI+BIcwFH5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cb28126d0f1489e87393416a1a7cae9953b584f636394ff341a78ee02773000","last_reissued_at":"2026-05-18T01:36:51.354588Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:36:51.354588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1502.05336","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":"2026-05-18T01:36:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UwOmtaElDcDjTap2iI2YQp1YGeAHAVuEDiHbKnn1UMSClUoHvFK1BiF1jZ0/yQkk8228KME0tnzZ666a6Te5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:53:26.346509Z"},"content_sha256":"bd0958f0e4747b948419843df957349747a31c891ee51e9261a0b2a92bb01d21","schema_version":"1.0","event_id":"sha256:bd0958f0e4747b948419843df957349747a31c891ee51e9261a0b2a92bb01d21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:HSZICJWQ6FEJ5BZZGQLKDJ6K5G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Jos\\'e Miguel Hern\\'andez-Lobato, Ryan P. Adams","submitted_at":"2015-02-18T18:45:17Z","abstract_excerpt":"Large multilayer neural networks trained with backpropagation have recently achieved state-of-the-art results in a wide range of problems. However, using backprop for neural net learning still has some disadvantages, e.g., having to tune a large number of hyperparameters to the data, lack of calibrated probabilistic predictions, and a tendency to overfit the training data. In principle, the Bayesian approach to learning neural networks does not have these problems. However, existing Bayesian techniques lack scalability to large dataset and network sizes. In this work we present a novel scalabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.05336","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":"2026-05-18T01:36:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+TUhzTVMDhfc/cEm2sYq89Gl8UoxCsUf8mvYKzpZLhpqxiEC03pkQORehutrVme5pypTJHYV9RrWSqs+rux0CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:53:26.346961Z"},"content_sha256":"9a8e3dcbc35f393fe367c9491bbb91871e3c0b9bfd128932b9f940b55db9b1c0","schema_version":"1.0","event_id":"sha256:9a8e3dcbc35f393fe367c9491bbb91871e3c0b9bfd128932b9f940b55db9b1c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HSZICJWQ6FEJ5BZZGQLKDJ6K5G/bundle.json","state_url":"https://pith.science/pith/HSZICJWQ6FEJ5BZZGQLKDJ6K5G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HSZICJWQ6FEJ5BZZGQLKDJ6K5G/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":"2026-08-04T21:53:26Z","links":{"resolver":"https://pith.science/pith/HSZICJWQ6FEJ5BZZGQLKDJ6K5G","bundle":"https://pith.science/pith/HSZICJWQ6FEJ5BZZGQLKDJ6K5G/bundle.json","state":"https://pith.science/pith/HSZICJWQ6FEJ5BZZGQLKDJ6K5G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HSZICJWQ6FEJ5BZZGQLKDJ6K5G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:HSZICJWQ6FEJ5BZZGQLKDJ6K5G","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":"15ed332b58754ce355c68a02c21c970a56d92647b02eb50b098cfe2642d68017","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-02-18T18:45:17Z","title_canon_sha256":"489c81a7b91abf6befbefed56bc516b730457c9e5e8f3bcc2a7dfde20829fddd"},"schema_version":"1.0","source":{"id":"1502.05336","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.05336","created_at":"2026-05-18T01:36:51Z"},{"alias_kind":"arxiv_version","alias_value":"1502.05336v2","created_at":"2026-05-18T01:36:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.05336","created_at":"2026-05-18T01:36:51Z"},{"alias_kind":"pith_short_12","alias_value":"HSZICJWQ6FEJ","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"HSZICJWQ6FEJ5BZZ","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"HSZICJWQ","created_at":"2026-05-18T12:29:25Z"}],"graph_snapshots":[{"event_id":"sha256:9a8e3dcbc35f393fe367c9491bbb91871e3c0b9bfd128932b9f940b55db9b1c0","target":"graph","created_at":"2026-05-18T01:36:51Z","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":"Large multilayer neural networks trained with backpropagation have recently achieved state-of-the-art results in a wide range of problems. However, using backprop for neural net learning still has some disadvantages, e.g., having to tune a large number of hyperparameters to the data, lack of calibrated probabilistic predictions, and a tendency to overfit the training data. In principle, the Bayesian approach to learning neural networks does not have these problems. However, existing Bayesian techniques lack scalability to large dataset and network sizes. In this work we present a novel scalabl","authors_text":"Jos\\'e Miguel Hern\\'andez-Lobato, Ryan P. Adams","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-02-18T18:45:17Z","title":"Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.05336","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:bd0958f0e4747b948419843df957349747a31c891ee51e9261a0b2a92bb01d21","target":"record","created_at":"2026-05-18T01:36:51Z","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":"15ed332b58754ce355c68a02c21c970a56d92647b02eb50b098cfe2642d68017","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-02-18T18:45:17Z","title_canon_sha256":"489c81a7b91abf6befbefed56bc516b730457c9e5e8f3bcc2a7dfde20829fddd"},"schema_version":"1.0","source":{"id":"1502.05336","kind":"arxiv","version":2}},"canonical_sha256":"3cb28126d0f1489e87393416a1a7cae9953b584f636394ff341a78ee02773000","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3cb28126d0f1489e87393416a1a7cae9953b584f636394ff341a78ee02773000","first_computed_at":"2026-05-18T01:36:51.354588Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:36:51.354588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9jZc2EjkZUbPIrMWcMpChy5K0ExQtHoQlGKnLhmCU9lOr9lIG6ifNSMtaDahFtzeg/JN6EjmsLvI+BIcwFH5AA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:36:51.355092Z","signed_message":"canonical_sha256_bytes"},"source_id":"1502.05336","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd0958f0e4747b948419843df957349747a31c891ee51e9261a0b2a92bb01d21","sha256:9a8e3dcbc35f393fe367c9491bbb91871e3c0b9bfd128932b9f940b55db9b1c0"],"state_sha256":"c1084caacc6cd8c989fdba6c842cabdcfa33630de1c85f6a635da2fc24524bb8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ns0cBrOPQ1zxb1exK47Uhx/yi2p3l6o/4mPwAczq/DaHLCRmmK06IMC8ChNWmPTSVswT/LdbOZvE9wlYr6YrAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:53:26.379385Z","bundle_sha256":"7909964b017e1aa0184b853abdf5d8184af5d9c48aed566fae969ebb00699399"}}