{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5HLKBG3HZVHKKBU5G4K5O4GZOO","short_pith_number":"pith:5HLKBG3H","canonical_record":{"source":{"id":"1805.07912","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-21T06:43:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f3522f2df2153c2ca9ca0a40f8e962c73dfd7518868a3ee700e353dc5eb2a811","abstract_canon_sha256":"f3f30065c6243f4d22afe989cdfe3e42c2d8be574d0af5374ddba86c5b852a86"},"schema_version":"1.0"},"canonical_sha256":"e9d6a09b67cd4ea5069d3715d770d9738da69511654c38344f8fb0372f214a71","source":{"kind":"arxiv","id":"1805.07912","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07912","created_at":"2026-05-17T23:55:03Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07912v3","created_at":"2026-05-17T23:55:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07912","created_at":"2026-05-17T23:55:03Z"},{"alias_kind":"pith_short_12","alias_value":"5HLKBG3HZVHK","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5HLKBG3HZVHKKBU5","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5HLKBG3H","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5HLKBG3HZVHKKBU5G4K5O4GZOO","target":"record","payload":{"canonical_record":{"source":{"id":"1805.07912","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-21T06:43:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f3522f2df2153c2ca9ca0a40f8e962c73dfd7518868a3ee700e353dc5eb2a811","abstract_canon_sha256":"f3f30065c6243f4d22afe989cdfe3e42c2d8be574d0af5374ddba86c5b852a86"},"schema_version":"1.0"},"canonical_sha256":"e9d6a09b67cd4ea5069d3715d770d9738da69511654c38344f8fb0372f214a71","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:03.504151Z","signature_b64":"yqp9ZGSJ7LVFIkYS3qQ1cpBdFuzHsVMXR56oqGnH4Ax872y+tYMkBuhB7NUOVfnbQWJVvaYfFWZrt3dHQM0vAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9d6a09b67cd4ea5069d3715d770d9738da69511654c38344f8fb0372f214a71","last_reissued_at":"2026-05-17T23:55:03.503738Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:03.503738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.07912","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:55:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"crBH6slcM/wHb6wq35coYJ+O4sN8EBlPTlKgHkFdppyRUTseIReqtluOuh103MC0F23c1ryy4Lzb9aZoXlASCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T00:25:41.124411Z"},"content_sha256":"85796a8a4d6b99b50e5695f5c70fa0c6d2aaacce7ec819f73cea019559f9920d","schema_version":"1.0","event_id":"sha256:85796a8a4d6b99b50e5695f5c70fa0c6d2aaacce7ec819f73cea019559f9920d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5HLKBG3HZVHKKBU5G4K5O4GZOO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bayesian posterior approximation via greedy particle optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Futoshi Futami, Issei Sato, Masashi Sugiyama, Zhenghang Cui","submitted_at":"2018-05-21T06:43:56Z","abstract_excerpt":"In Bayesian inference, the posterior distributions are difficult to obtain analytically for complex models such as neural networks. Variational inference usually uses a parametric distribution for approximation, from which we can easily draw samples. Recently discrete approximation by particles has attracted attention because of its high expression ability. An example is Stein variational gradient descent (SVGD), which iteratively optimizes particles. Although SVGD has been shown to be computationally efficient empirically, its theoretical properties have not been clarified yet and no finite s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07912","kind":"arxiv","version":3},"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":"2026-05-17T23:55:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BPmG8tRJDiQP7T/munF5DGGqCeZrI27C6JVf/qW1jN0VtkM/kzhD6sC0Vn7+d+AyVL14cX6k2tMGbCgnHrkgCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T00:25:41.124776Z"},"content_sha256":"ced8bcaf3989a2e0b6c5ba93286f22b5ed9fc4f608551a207ccb29f5810c531b","schema_version":"1.0","event_id":"sha256:ced8bcaf3989a2e0b6c5ba93286f22b5ed9fc4f608551a207ccb29f5810c531b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5HLKBG3HZVHKKBU5G4K5O4GZOO/bundle.json","state_url":"https://pith.science/pith/5HLKBG3HZVHKKBU5G4K5O4GZOO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5HLKBG3HZVHKKBU5G4K5O4GZOO/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":"2026-05-28T00:25:41Z","links":{"resolver":"https://pith.science/pith/5HLKBG3HZVHKKBU5G4K5O4GZOO","bundle":"https://pith.science/pith/5HLKBG3HZVHKKBU5G4K5O4GZOO/bundle.json","state":"https://pith.science/pith/5HLKBG3HZVHKKBU5G4K5O4GZOO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5HLKBG3HZVHKKBU5G4K5O4GZOO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5HLKBG3HZVHKKBU5G4K5O4GZOO","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":"f3f30065c6243f4d22afe989cdfe3e42c2d8be574d0af5374ddba86c5b852a86","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-21T06:43:56Z","title_canon_sha256":"f3522f2df2153c2ca9ca0a40f8e962c73dfd7518868a3ee700e353dc5eb2a811"},"schema_version":"1.0","source":{"id":"1805.07912","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07912","created_at":"2026-05-17T23:55:03Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07912v3","created_at":"2026-05-17T23:55:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07912","created_at":"2026-05-17T23:55:03Z"},{"alias_kind":"pith_short_12","alias_value":"5HLKBG3HZVHK","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5HLKBG3HZVHKKBU5","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5HLKBG3H","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:ced8bcaf3989a2e0b6c5ba93286f22b5ed9fc4f608551a207ccb29f5810c531b","target":"graph","created_at":"2026-05-17T23:55:03Z","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":"In Bayesian inference, the posterior distributions are difficult to obtain analytically for complex models such as neural networks. Variational inference usually uses a parametric distribution for approximation, from which we can easily draw samples. Recently discrete approximation by particles has attracted attention because of its high expression ability. An example is Stein variational gradient descent (SVGD), which iteratively optimizes particles. Although SVGD has been shown to be computationally efficient empirically, its theoretical properties have not been clarified yet and no finite s","authors_text":"Futoshi Futami, Issei Sato, Masashi Sugiyama, Zhenghang Cui","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-21T06:43:56Z","title":"Bayesian posterior approximation via greedy particle optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07912","kind":"arxiv","version":3},"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":"sha256:85796a8a4d6b99b50e5695f5c70fa0c6d2aaacce7ec819f73cea019559f9920d","target":"record","created_at":"2026-05-17T23:55:03Z","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":"f3f30065c6243f4d22afe989cdfe3e42c2d8be574d0af5374ddba86c5b852a86","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-21T06:43:56Z","title_canon_sha256":"f3522f2df2153c2ca9ca0a40f8e962c73dfd7518868a3ee700e353dc5eb2a811"},"schema_version":"1.0","source":{"id":"1805.07912","kind":"arxiv","version":3}},"canonical_sha256":"e9d6a09b67cd4ea5069d3715d770d9738da69511654c38344f8fb0372f214a71","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9d6a09b67cd4ea5069d3715d770d9738da69511654c38344f8fb0372f214a71","first_computed_at":"2026-05-17T23:55:03.503738Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:03.503738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yqp9ZGSJ7LVFIkYS3qQ1cpBdFuzHsVMXR56oqGnH4Ax872y+tYMkBuhB7NUOVfnbQWJVvaYfFWZrt3dHQM0vAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:03.504151Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.07912","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85796a8a4d6b99b50e5695f5c70fa0c6d2aaacce7ec819f73cea019559f9920d","sha256:ced8bcaf3989a2e0b6c5ba93286f22b5ed9fc4f608551a207ccb29f5810c531b"],"state_sha256":"1fb5e4369730f29234d9c7cf6f04b072bbf23616efe52d8f9e1c8ea1031f22ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F2fwnxMCZceWGrDaEjOzHCZOkuDmt7ZsAE1EqvOFs8SHy3DR8qjF4hvS7GvQzOsEoEWZXu0bYOTRfdza0gE4Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T00:25:41.126989Z","bundle_sha256":"eed81bfa7ee218cf4da9b6f60bd8de29ba515baddd544682dd24572c50b95887"}}