{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:O2HCSKFHKU5AIKCMVMBS6FEJF7","short_pith_number":"pith:O2HCSKFH","canonical_record":{"source":{"id":"1909.00719","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-02T13:54:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"65cd9a6b89f0e7cb236ab63be88b646f2e838b24d6bb7ead29b351052ca8ed86","abstract_canon_sha256":"56e95cd9c0ac8eeedef41639bc1dcb52526202e9b29181f05e5c62befbcea0fb"},"schema_version":"1.0"},"canonical_sha256":"768e2928a7553a04284cab032f14892fe9726e8e445f62a2663440ac1110e4ff","source":{"kind":"arxiv","id":"1909.00719","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.00719","created_at":"2026-07-05T01:45:24Z"},{"alias_kind":"arxiv_version","alias_value":"1909.00719v4","created_at":"2026-07-05T01:45:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00719","created_at":"2026-07-05T01:45:24Z"},{"alias_kind":"pith_short_12","alias_value":"O2HCSKFHKU5A","created_at":"2026-07-05T01:45:24Z"},{"alias_kind":"pith_short_16","alias_value":"O2HCSKFHKU5AIKCM","created_at":"2026-07-05T01:45:24Z"},{"alias_kind":"pith_short_8","alias_value":"O2HCSKFH","created_at":"2026-07-05T01:45:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:O2HCSKFHKU5AIKCMVMBS6FEJF7","target":"record","payload":{"canonical_record":{"source":{"id":"1909.00719","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-02T13:54:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"65cd9a6b89f0e7cb236ab63be88b646f2e838b24d6bb7ead29b351052ca8ed86","abstract_canon_sha256":"56e95cd9c0ac8eeedef41639bc1dcb52526202e9b29181f05e5c62befbcea0fb"},"schema_version":"1.0"},"canonical_sha256":"768e2928a7553a04284cab032f14892fe9726e8e445f62a2663440ac1110e4ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:24.097641Z","signature_b64":"QVkDX0b5FsA8wbgmxGvgoXXTGYNGfZMGu3FfJU5UtZvchK63mVYW9ZFwdcFtAQhzr1gkkHddcuwftiRF7bmfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"768e2928a7553a04284cab032f14892fe9726e8e445f62a2663440ac1110e4ff","last_reissued_at":"2026-07-05T01:45:24.097204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:24.097204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.00719","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":"2026-07-05T01:45:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"66ONEs9a9zrObRYCiZwZnN/sw3H9nTs5xdDNPP+d/Acn06X9Wn4hT6s+SOanMnaVLrpsVyjmfi9y6njGEMjcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:05:51.077260Z"},"content_sha256":"92c26d20e9b9bf9d22eb8255b53685a76f88729f3ed4c72ae544812da4029278","schema_version":"1.0","event_id":"sha256:92c26d20e9b9bf9d22eb8255b53685a76f88729f3ed4c72ae544812da4029278"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:O2HCSKFHKU5AIKCMVMBS6FEJF7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Expressiveness of Approximate Inference in Bayesian Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrew Y. K. Foong, David R. Burt, Richard E. Turner, Yingzhen Li","submitted_at":"2019-09-02T13:54:39Z","abstract_excerpt":"While Bayesian neural networks (BNNs) hold the promise of being flexible, well-calibrated statistical models, inference often requires approximations whose consequences are poorly understood. We study the quality of common variational methods in approximating the Bayesian predictive distribution. For single-hidden layer ReLU BNNs, we prove a fundamental limitation in function-space of two of the most commonly used distributions defined in weight-space: mean-field Gaussian and Monte Carlo dropout. We find there are simple cases where neither method can have substantially increased uncertainty i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00719","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/1909.00719/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":"2026-07-05T01:45:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ce8+zAGutC8EPZ8h6BxAvNegsa2OlMr3oyhOQ/T/JNE259P/gVkoiJbUfwBD7Rm+sFrnbidKa4uClZX4OqaNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:05:51.077652Z"},"content_sha256":"633d45f257379d89dbbfdbf051c2835e37a00a1c90aa6956ba0634818f7d8554","schema_version":"1.0","event_id":"sha256:633d45f257379d89dbbfdbf051c2835e37a00a1c90aa6956ba0634818f7d8554"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O2HCSKFHKU5AIKCMVMBS6FEJF7/bundle.json","state_url":"https://pith.science/pith/O2HCSKFHKU5AIKCMVMBS6FEJF7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O2HCSKFHKU5AIKCMVMBS6FEJF7/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":"2026-07-06T13:05:51Z","links":{"resolver":"https://pith.science/pith/O2HCSKFHKU5AIKCMVMBS6FEJF7","bundle":"https://pith.science/pith/O2HCSKFHKU5AIKCMVMBS6FEJF7/bundle.json","state":"https://pith.science/pith/O2HCSKFHKU5AIKCMVMBS6FEJF7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O2HCSKFHKU5AIKCMVMBS6FEJF7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:O2HCSKFHKU5AIKCMVMBS6FEJF7","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":"56e95cd9c0ac8eeedef41639bc1dcb52526202e9b29181f05e5c62befbcea0fb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-02T13:54:39Z","title_canon_sha256":"65cd9a6b89f0e7cb236ab63be88b646f2e838b24d6bb7ead29b351052ca8ed86"},"schema_version":"1.0","source":{"id":"1909.00719","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.00719","created_at":"2026-07-05T01:45:24Z"},{"alias_kind":"arxiv_version","alias_value":"1909.00719v4","created_at":"2026-07-05T01:45:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00719","created_at":"2026-07-05T01:45:24Z"},{"alias_kind":"pith_short_12","alias_value":"O2HCSKFHKU5A","created_at":"2026-07-05T01:45:24Z"},{"alias_kind":"pith_short_16","alias_value":"O2HCSKFHKU5AIKCM","created_at":"2026-07-05T01:45:24Z"},{"alias_kind":"pith_short_8","alias_value":"O2HCSKFH","created_at":"2026-07-05T01:45:24Z"}],"graph_snapshots":[{"event_id":"sha256:633d45f257379d89dbbfdbf051c2835e37a00a1c90aa6956ba0634818f7d8554","target":"graph","created_at":"2026-07-05T01:45:24Z","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/1909.00719/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Bayesian neural networks (BNNs) hold the promise of being flexible, well-calibrated statistical models, inference often requires approximations whose consequences are poorly understood. We study the quality of common variational methods in approximating the Bayesian predictive distribution. For single-hidden layer ReLU BNNs, we prove a fundamental limitation in function-space of two of the most commonly used distributions defined in weight-space: mean-field Gaussian and Monte Carlo dropout. We find there are simple cases where neither method can have substantially increased uncertainty i","authors_text":"Andrew Y. K. Foong, David R. Burt, Richard E. Turner, Yingzhen Li","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-02T13:54:39Z","title":"On the Expressiveness of Approximate Inference in Bayesian Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00719","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":"sha256:92c26d20e9b9bf9d22eb8255b53685a76f88729f3ed4c72ae544812da4029278","target":"record","created_at":"2026-07-05T01:45:24Z","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":"56e95cd9c0ac8eeedef41639bc1dcb52526202e9b29181f05e5c62befbcea0fb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-02T13:54:39Z","title_canon_sha256":"65cd9a6b89f0e7cb236ab63be88b646f2e838b24d6bb7ead29b351052ca8ed86"},"schema_version":"1.0","source":{"id":"1909.00719","kind":"arxiv","version":4}},"canonical_sha256":"768e2928a7553a04284cab032f14892fe9726e8e445f62a2663440ac1110e4ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"768e2928a7553a04284cab032f14892fe9726e8e445f62a2663440ac1110e4ff","first_computed_at":"2026-07-05T01:45:24.097204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:24.097204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QVkDX0b5FsA8wbgmxGvgoXXTGYNGfZMGu3FfJU5UtZvchK63mVYW9ZFwdcFtAQhzr1gkkHddcuwftiRF7bmfDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:24.097641Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.00719","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92c26d20e9b9bf9d22eb8255b53685a76f88729f3ed4c72ae544812da4029278","sha256:633d45f257379d89dbbfdbf051c2835e37a00a1c90aa6956ba0634818f7d8554"],"state_sha256":"dcde84158eb1cdc13e1cf323ba67c84a5c1368b3b2cdadd86507b544cb525ee7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MHKEqm2mfPAbhsLc+L/u14G3lWHwPlVcdT6gxutTui+i1lkrNmr/jeSBOJtAt87PQ9brGM14ZpYzkZD0eqeOAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T13:05:51.079685Z","bundle_sha256":"16b6c79b5fb9842942048bb27a288100e5ad0baf9d780a6c0558c533962f4743"}}