{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:F4BHDZKWSZ55EJSEYRQ37T6CMF","short_pith_number":"pith:F4BHDZKW","canonical_record":{"source":{"id":"1806.03563","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-10T00:58:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c0d2553f94ee2f997fff434f14b4070311791fce28f4e32f04e17a64a83e7ebf","abstract_canon_sha256":"98157eff42f2769cbb29b3a10c71812f1aab59d91e3a33fac350564618ad3aa2"},"schema_version":"1.0"},"canonical_sha256":"2f0271e556967bd22644c461bfcfc2614ab059e2da9337030271b3918bed0100","source":{"kind":"arxiv","id":"1806.03563","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.03563","created_at":"2026-05-18T00:13:42Z"},{"alias_kind":"arxiv_version","alias_value":"1806.03563v1","created_at":"2026-05-18T00:13:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03563","created_at":"2026-05-18T00:13:42Z"},{"alias_kind":"pith_short_12","alias_value":"F4BHDZKWSZ55","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"F4BHDZKWSZ55EJSE","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"F4BHDZKW","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:F4BHDZKWSZ55EJSEYRQ37T6CMF","target":"record","payload":{"canonical_record":{"source":{"id":"1806.03563","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-10T00:58:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c0d2553f94ee2f997fff434f14b4070311791fce28f4e32f04e17a64a83e7ebf","abstract_canon_sha256":"98157eff42f2769cbb29b3a10c71812f1aab59d91e3a33fac350564618ad3aa2"},"schema_version":"1.0"},"canonical_sha256":"2f0271e556967bd22644c461bfcfc2614ab059e2da9337030271b3918bed0100","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:42.968688Z","signature_b64":"cKFXPLks0ohM61+EeTH24w5nErLlbJvasMcHAJGkj9VmiUCHNkZjkYE8LrVxi1hE+9d2WOamuZ1+ITIwlTUGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f0271e556967bd22644c461bfcfc2614ab059e2da9337030271b3918bed0100","last_reissued_at":"2026-05-18T00:13:42.968075Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:42.968075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.03563","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":"2026-05-18T00:13:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hfj7IBHE6Ul5zoTkb5Dqui4cAKxI4LEHSOirzJOtPopp3Q7jS/renwwOYtxeVoDuT52e1kYL2o4l7nSiVNUAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T13:44:08.451596Z"},"content_sha256":"621e618ae965a6628cce28080e51679743c0548697edff4090e5e19063339ed4","schema_version":"1.0","event_id":"sha256:621e618ae965a6628cce28080e51679743c0548697edff4090e5e19063339ed4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:F4BHDZKWSZ55EJSEYRQ37T6CMF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Building Bayesian Neural Networks with Blocks: On Structure, Interpretability and Uncertainty","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Hao Henry Zhou, Vikas Singh, Yunyang Xiong","submitted_at":"2018-06-10T00:58:58Z","abstract_excerpt":"We provide simple schemes to build Bayesian Neural Networks (BNNs), block by block, inspired by a recent idea of computation skeletons. We show how by adjusting the types of blocks that are used within the computation skeleton, we can identify interesting relationships with Deep Gaussian Processes (DGPs), deep kernel learning (DKL), random features type approximation and other topics. We give strategies to approximate the posterior via doubly stochastic variational inference for such models which yield uncertainty estimates. We give a detailed theoretical analysis and point out extensions that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03563","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":"2026-05-18T00:13:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3SchNu4ulLZdcmv77y7Ser9OEZKRhmjyycq5/iVEPE2/84P3O2wiFoqfDIIiMVQgSM61uuLNVU8JPEFYY89mDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T13:44:08.451950Z"},"content_sha256":"2f99049145a750a14dfc5762f8af2ecdb85abcd405b39623f31b886d2e6f03e0","schema_version":"1.0","event_id":"sha256:2f99049145a750a14dfc5762f8af2ecdb85abcd405b39623f31b886d2e6f03e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F4BHDZKWSZ55EJSEYRQ37T6CMF/bundle.json","state_url":"https://pith.science/pith/F4BHDZKWSZ55EJSEYRQ37T6CMF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F4BHDZKWSZ55EJSEYRQ37T6CMF/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":"2026-06-01T13:44:08Z","links":{"resolver":"https://pith.science/pith/F4BHDZKWSZ55EJSEYRQ37T6CMF","bundle":"https://pith.science/pith/F4BHDZKWSZ55EJSEYRQ37T6CMF/bundle.json","state":"https://pith.science/pith/F4BHDZKWSZ55EJSEYRQ37T6CMF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F4BHDZKWSZ55EJSEYRQ37T6CMF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:F4BHDZKWSZ55EJSEYRQ37T6CMF","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":"98157eff42f2769cbb29b3a10c71812f1aab59d91e3a33fac350564618ad3aa2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-10T00:58:58Z","title_canon_sha256":"c0d2553f94ee2f997fff434f14b4070311791fce28f4e32f04e17a64a83e7ebf"},"schema_version":"1.0","source":{"id":"1806.03563","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.03563","created_at":"2026-05-18T00:13:42Z"},{"alias_kind":"arxiv_version","alias_value":"1806.03563v1","created_at":"2026-05-18T00:13:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03563","created_at":"2026-05-18T00:13:42Z"},{"alias_kind":"pith_short_12","alias_value":"F4BHDZKWSZ55","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"F4BHDZKWSZ55EJSE","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"F4BHDZKW","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:2f99049145a750a14dfc5762f8af2ecdb85abcd405b39623f31b886d2e6f03e0","target":"graph","created_at":"2026-05-18T00:13:42Z","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":"We provide simple schemes to build Bayesian Neural Networks (BNNs), block by block, inspired by a recent idea of computation skeletons. We show how by adjusting the types of blocks that are used within the computation skeleton, we can identify interesting relationships with Deep Gaussian Processes (DGPs), deep kernel learning (DKL), random features type approximation and other topics. We give strategies to approximate the posterior via doubly stochastic variational inference for such models which yield uncertainty estimates. We give a detailed theoretical analysis and point out extensions that","authors_text":"Hao Henry Zhou, Vikas Singh, Yunyang Xiong","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-10T00:58:58Z","title":"Building Bayesian Neural Networks with Blocks: On Structure, Interpretability and Uncertainty"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03563","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":"sha256:621e618ae965a6628cce28080e51679743c0548697edff4090e5e19063339ed4","target":"record","created_at":"2026-05-18T00:13:42Z","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":"98157eff42f2769cbb29b3a10c71812f1aab59d91e3a33fac350564618ad3aa2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-10T00:58:58Z","title_canon_sha256":"c0d2553f94ee2f997fff434f14b4070311791fce28f4e32f04e17a64a83e7ebf"},"schema_version":"1.0","source":{"id":"1806.03563","kind":"arxiv","version":1}},"canonical_sha256":"2f0271e556967bd22644c461bfcfc2614ab059e2da9337030271b3918bed0100","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f0271e556967bd22644c461bfcfc2614ab059e2da9337030271b3918bed0100","first_computed_at":"2026-05-18T00:13:42.968075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:42.968075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cKFXPLks0ohM61+EeTH24w5nErLlbJvasMcHAJGkj9VmiUCHNkZjkYE8LrVxi1hE+9d2WOamuZ1+ITIwlTUGDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:42.968688Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.03563","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:621e618ae965a6628cce28080e51679743c0548697edff4090e5e19063339ed4","sha256:2f99049145a750a14dfc5762f8af2ecdb85abcd405b39623f31b886d2e6f03e0"],"state_sha256":"874479a897f5ad76b272061a13a87dd44339637f7aa84206da34cd1d3a489df4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WxU/HWHe3qBYhSBqIZMbwKUaAZ546pU9wA1OCXMlrE8hs+AloY4CaXw9x0toAT3YU+0Ywhl4VpiBBaQ70PijCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T13:44:08.454012Z","bundle_sha256":"e6cf828237f05de4370f7f5cbb749e5bad0fea03f5dd6b1d887c9fe35a49b4b2"}}