{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:2QLFYRFUOGNLGUOM2BMT4WY7T6","short_pith_number":"pith:2QLFYRFU","canonical_record":{"source":{"id":"1902.09754","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-26T06:39:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7150c0f90d1f8af97b1747bfaec915cba34964c9c10c36cfc256662ecf40fe2c","abstract_canon_sha256":"494cf8f20efb6ff33b874f9016ee9870163c2e50d79f595309c34deb36c9ffa0"},"schema_version":"1.0"},"canonical_sha256":"d4165c44b4719ab351ccd0593e5b1f9fb4a77f2abab828c7466e720d13f8a7c0","source":{"kind":"arxiv","id":"1902.09754","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.09754","created_at":"2026-05-17T23:46:41Z"},{"alias_kind":"arxiv_version","alias_value":"1902.09754v2","created_at":"2026-05-17T23:46:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09754","created_at":"2026-05-17T23:46:41Z"},{"alias_kind":"pith_short_12","alias_value":"2QLFYRFUOGNL","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2QLFYRFUOGNLGUOM","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2QLFYRFU","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:2QLFYRFUOGNLGUOM2BMT4WY7T6","target":"record","payload":{"canonical_record":{"source":{"id":"1902.09754","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-26T06:39:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7150c0f90d1f8af97b1747bfaec915cba34964c9c10c36cfc256662ecf40fe2c","abstract_canon_sha256":"494cf8f20efb6ff33b874f9016ee9870163c2e50d79f595309c34deb36c9ffa0"},"schema_version":"1.0"},"canonical_sha256":"d4165c44b4719ab351ccd0593e5b1f9fb4a77f2abab828c7466e720d13f8a7c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:41.040068Z","signature_b64":"/b1rjO83pv8l/hch+DxIka7H+ChFJgbwvaSOaEpLHhgVuitrWbsStU/cFAPC8oE3xxk8GycS6FDcRwSU7mRMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4165c44b4719ab351ccd0593e5b1f9fb4a77f2abab828c7466e720d13f8a7c0","last_reissued_at":"2026-05-17T23:46:41.039292Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:41.039292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.09754","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":"2026-05-17T23:46:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jiu5p1EQ4dJu1I1xcbxlnSAcGmYse/FwOgrYpzGnUleF0bPuviHBZ4nmZD9BcIguz+QfAiQuPxlmyjwnzOqbCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:41:15.526937Z"},"content_sha256":"0b532011694c6672931fe191bbd6719ba5b88a053e1294880c34f7e9c312c895","schema_version":"1.0","event_id":"sha256:0b532011694c6672931fe191bbd6719ba5b88a053e1294880c34f7e9c312c895"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:2QLFYRFUOGNLGUOM2BMT4WY7T6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Function Space Particle Optimization for Bayesian Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bo Zhang, Jun Zhu, Tongzheng Ren, Ziyu Wang","submitted_at":"2019-02-26T06:39:42Z","abstract_excerpt":"While Bayesian neural networks (BNNs) have drawn increasing attention, their posterior inference remains challenging, due to the high-dimensional and over-parameterized nature. To address this issue, several highly flexible and scalable variational inference procedures based on the idea of particle optimization have been proposed. These methods directly optimize a set of particles to approximate the target posterior. However, their application to BNNs often yields sub-optimal performance, as such methods have a particular failure mode on over-parameterized models. In this paper, we propose to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09754","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":"2026-05-17T23:46:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/yAGXgSH0Pg0f4L248kjYhpEZFwcRfWpwVHsw0HEkDgBdxq/PTfaeoNoa9W8G12WGhWs9NdaQxauw03wxOHWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:41:15.527282Z"},"content_sha256":"5d0bc21e804a65c1e281777dbeacc32e45d997675f23b8a4a34e05a109d08c12","schema_version":"1.0","event_id":"sha256:5d0bc21e804a65c1e281777dbeacc32e45d997675f23b8a4a34e05a109d08c12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2QLFYRFUOGNLGUOM2BMT4WY7T6/bundle.json","state_url":"https://pith.science/pith/2QLFYRFUOGNLGUOM2BMT4WY7T6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2QLFYRFUOGNLGUOM2BMT4WY7T6/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":"2026-05-30T08:41:15Z","links":{"resolver":"https://pith.science/pith/2QLFYRFUOGNLGUOM2BMT4WY7T6","bundle":"https://pith.science/pith/2QLFYRFUOGNLGUOM2BMT4WY7T6/bundle.json","state":"https://pith.science/pith/2QLFYRFUOGNLGUOM2BMT4WY7T6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2QLFYRFUOGNLGUOM2BMT4WY7T6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:2QLFYRFUOGNLGUOM2BMT4WY7T6","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":"494cf8f20efb6ff33b874f9016ee9870163c2e50d79f595309c34deb36c9ffa0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-26T06:39:42Z","title_canon_sha256":"7150c0f90d1f8af97b1747bfaec915cba34964c9c10c36cfc256662ecf40fe2c"},"schema_version":"1.0","source":{"id":"1902.09754","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.09754","created_at":"2026-05-17T23:46:41Z"},{"alias_kind":"arxiv_version","alias_value":"1902.09754v2","created_at":"2026-05-17T23:46:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09754","created_at":"2026-05-17T23:46:41Z"},{"alias_kind":"pith_short_12","alias_value":"2QLFYRFUOGNL","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2QLFYRFUOGNLGUOM","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2QLFYRFU","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:5d0bc21e804a65c1e281777dbeacc32e45d997675f23b8a4a34e05a109d08c12","target":"graph","created_at":"2026-05-17T23:46:41Z","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":"While Bayesian neural networks (BNNs) have drawn increasing attention, their posterior inference remains challenging, due to the high-dimensional and over-parameterized nature. To address this issue, several highly flexible and scalable variational inference procedures based on the idea of particle optimization have been proposed. These methods directly optimize a set of particles to approximate the target posterior. However, their application to BNNs often yields sub-optimal performance, as such methods have a particular failure mode on over-parameterized models. In this paper, we propose to ","authors_text":"Bo Zhang, Jun Zhu, Tongzheng Ren, Ziyu Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-26T06:39:42Z","title":"Function Space Particle Optimization for Bayesian Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09754","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":"sha256:0b532011694c6672931fe191bbd6719ba5b88a053e1294880c34f7e9c312c895","target":"record","created_at":"2026-05-17T23:46:41Z","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":"494cf8f20efb6ff33b874f9016ee9870163c2e50d79f595309c34deb36c9ffa0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-26T06:39:42Z","title_canon_sha256":"7150c0f90d1f8af97b1747bfaec915cba34964c9c10c36cfc256662ecf40fe2c"},"schema_version":"1.0","source":{"id":"1902.09754","kind":"arxiv","version":2}},"canonical_sha256":"d4165c44b4719ab351ccd0593e5b1f9fb4a77f2abab828c7466e720d13f8a7c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4165c44b4719ab351ccd0593e5b1f9fb4a77f2abab828c7466e720d13f8a7c0","first_computed_at":"2026-05-17T23:46:41.039292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:41.039292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/b1rjO83pv8l/hch+DxIka7H+ChFJgbwvaSOaEpLHhgVuitrWbsStU/cFAPC8oE3xxk8GycS6FDcRwSU7mRMDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:41.040068Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.09754","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b532011694c6672931fe191bbd6719ba5b88a053e1294880c34f7e9c312c895","sha256:5d0bc21e804a65c1e281777dbeacc32e45d997675f23b8a4a34e05a109d08c12"],"state_sha256":"7694fb58ac5b8c609f3916d352ddceab4cd80a096920cd71d732826544aad3bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G/wc7Vg259oVCyayFWYLCNDpPkst2n+2rTEiUNfvEhZugB4VmuUyp+HMcLL8kBU7edOMmWL9ECd8lHb0BL/UAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T08:41:15.529269Z","bundle_sha256":"6d314f3df7b6bab420e3d019f75ccf7fa5dab14cc01daf44af2351664fbb2fc9"}}