{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:NJMRWIEHVKQC3DLF3GBHUKCVUP","short_pith_number":"pith:NJMRWIEH","canonical_record":{"source":{"id":"2205.15902","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-05-31T15:53:15Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"9d10ac66a1e701eb29d4769a80210d61a9214af63d40e8d5dd4b46be2bbfc6f2","abstract_canon_sha256":"488a75095fff9bd8a6329df96af8b2fec97b9dd29de26a9632728b03cbc88e0a"},"schema_version":"1.0"},"canonical_sha256":"6a591b2087aaa02d8d65d9827a2855a3e6bb6dde9bd6963ab704a4fc7aa6615d","source":{"kind":"arxiv","id":"2205.15902","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15902","created_at":"2026-07-05T06:03:08Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15902v3","created_at":"2026-07-05T06:03:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15902","created_at":"2026-07-05T06:03:08Z"},{"alias_kind":"pith_short_12","alias_value":"NJMRWIEHVKQC","created_at":"2026-07-05T06:03:08Z"},{"alias_kind":"pith_short_16","alias_value":"NJMRWIEHVKQC3DLF","created_at":"2026-07-05T06:03:08Z"},{"alias_kind":"pith_short_8","alias_value":"NJMRWIEH","created_at":"2026-07-05T06:03:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:NJMRWIEHVKQC3DLF3GBHUKCVUP","target":"record","payload":{"canonical_record":{"source":{"id":"2205.15902","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-05-31T15:53:15Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"9d10ac66a1e701eb29d4769a80210d61a9214af63d40e8d5dd4b46be2bbfc6f2","abstract_canon_sha256":"488a75095fff9bd8a6329df96af8b2fec97b9dd29de26a9632728b03cbc88e0a"},"schema_version":"1.0"},"canonical_sha256":"6a591b2087aaa02d8d65d9827a2855a3e6bb6dde9bd6963ab704a4fc7aa6615d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:08.559780Z","signature_b64":"Q5U20X9LltJAcYJSW9+BudnIAUonLSVyFy3GTA/4ZXZ4GznEumMGSAhX/+JmLZfF/53n8qIAPFm4uyBX9wcZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a591b2087aaa02d8d65d9827a2855a3e6bb6dde9bd6963ab704a4fc7aa6615d","last_reissued_at":"2026-07-05T06:03:08.559359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:08.559359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.15902","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":"2026-07-05T06:03:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZAtSYbPcIFh9a4Hs/Q7r2tAB+jCwD41qgHCU7G3e3LDmaUAw32ihWMQSXDg6NULI3ngUsy0ZrzZlpQYBiXYTCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T02:42:21.444780Z"},"content_sha256":"871f40f5531286e458e2aff3e2d0703c8d553c0fec58596f9a1c5cab53d01edf","schema_version":"1.0","event_id":"sha256:871f40f5531286e458e2aff3e2d0703c8d553c0fec58596f9a1c5cab53d01edf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:NJMRWIEHVKQC3DLF3GBHUKCVUP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variational inference via Wasserstein gradient flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Francis Bach, Marc Lambert, Philippe Rigollet, Silv\\`ere Bonnabel, Sinho Chewi","submitted_at":"2022-05-31T15:53:15Z","abstract_excerpt":"Along with Markov chain Monte Carlo (MCMC) methods, variational inference (VI) has emerged as a central computational approach to large-scale Bayesian inference. Rather than sampling from the true posterior $\\pi$, VI aims at producing a simple but effective approximation $\\hat \\pi$ to $\\pi$ for which summary statistics are easy to compute. However, unlike the well-studied MCMC methodology, algorithmic guarantees for VI are still relatively less well-understood. In this work, we propose principled methods for VI, in which $\\hat \\pi$ is taken to be a Gaussian or a mixture of Gaussians, which res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15902","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.15902/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":"2026-07-05T06:03:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S+kzq5ea6xQu5wUIlSFqi82zg6BZs/WZvgys/LJT3If0zLNbXDDyqvF2j52r/NOF6GW9ONiwwkK5fC5cFucoBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T02:42:21.445313Z"},"content_sha256":"ae5e81f6c77639878f2251bed65c2ab5001ffbc1d457ad1190f2216acdccbd6b","schema_version":"1.0","event_id":"sha256:ae5e81f6c77639878f2251bed65c2ab5001ffbc1d457ad1190f2216acdccbd6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NJMRWIEHVKQC3DLF3GBHUKCVUP/bundle.json","state_url":"https://pith.science/pith/NJMRWIEHVKQC3DLF3GBHUKCVUP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NJMRWIEHVKQC3DLF3GBHUKCVUP/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":"2026-08-17T02:42:21Z","links":{"resolver":"https://pith.science/pith/NJMRWIEHVKQC3DLF3GBHUKCVUP","bundle":"https://pith.science/pith/NJMRWIEHVKQC3DLF3GBHUKCVUP/bundle.json","state":"https://pith.science/pith/NJMRWIEHVKQC3DLF3GBHUKCVUP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NJMRWIEHVKQC3DLF3GBHUKCVUP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NJMRWIEHVKQC3DLF3GBHUKCVUP","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":"488a75095fff9bd8a6329df96af8b2fec97b9dd29de26a9632728b03cbc88e0a","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-05-31T15:53:15Z","title_canon_sha256":"9d10ac66a1e701eb29d4769a80210d61a9214af63d40e8d5dd4b46be2bbfc6f2"},"schema_version":"1.0","source":{"id":"2205.15902","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15902","created_at":"2026-07-05T06:03:08Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15902v3","created_at":"2026-07-05T06:03:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15902","created_at":"2026-07-05T06:03:08Z"},{"alias_kind":"pith_short_12","alias_value":"NJMRWIEHVKQC","created_at":"2026-07-05T06:03:08Z"},{"alias_kind":"pith_short_16","alias_value":"NJMRWIEHVKQC3DLF","created_at":"2026-07-05T06:03:08Z"},{"alias_kind":"pith_short_8","alias_value":"NJMRWIEH","created_at":"2026-07-05T06:03:08Z"}],"graph_snapshots":[{"event_id":"sha256:ae5e81f6c77639878f2251bed65c2ab5001ffbc1d457ad1190f2216acdccbd6b","target":"graph","created_at":"2026-07-05T06:03:08Z","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/2205.15902/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Along with Markov chain Monte Carlo (MCMC) methods, variational inference (VI) has emerged as a central computational approach to large-scale Bayesian inference. Rather than sampling from the true posterior $\\pi$, VI aims at producing a simple but effective approximation $\\hat \\pi$ to $\\pi$ for which summary statistics are easy to compute. However, unlike the well-studied MCMC methodology, algorithmic guarantees for VI are still relatively less well-understood. In this work, we propose principled methods for VI, in which $\\hat \\pi$ is taken to be a Gaussian or a mixture of Gaussians, which res","authors_text":"Francis Bach, Marc Lambert, Philippe Rigollet, Silv\\`ere Bonnabel, Sinho Chewi","cross_cats":["cs.LG","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-05-31T15:53:15Z","title":"Variational inference via Wasserstein gradient flows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15902","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":"sha256:871f40f5531286e458e2aff3e2d0703c8d553c0fec58596f9a1c5cab53d01edf","target":"record","created_at":"2026-07-05T06:03:08Z","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":"488a75095fff9bd8a6329df96af8b2fec97b9dd29de26a9632728b03cbc88e0a","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-05-31T15:53:15Z","title_canon_sha256":"9d10ac66a1e701eb29d4769a80210d61a9214af63d40e8d5dd4b46be2bbfc6f2"},"schema_version":"1.0","source":{"id":"2205.15902","kind":"arxiv","version":3}},"canonical_sha256":"6a591b2087aaa02d8d65d9827a2855a3e6bb6dde9bd6963ab704a4fc7aa6615d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a591b2087aaa02d8d65d9827a2855a3e6bb6dde9bd6963ab704a4fc7aa6615d","first_computed_at":"2026-07-05T06:03:08.559359Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:03:08.559359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q5U20X9LltJAcYJSW9+BudnIAUonLSVyFy3GTA/4ZXZ4GznEumMGSAhX/+JmLZfF/53n8qIAPFm4uyBX9wcZDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:03:08.559780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.15902","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:871f40f5531286e458e2aff3e2d0703c8d553c0fec58596f9a1c5cab53d01edf","sha256:ae5e81f6c77639878f2251bed65c2ab5001ffbc1d457ad1190f2216acdccbd6b"],"state_sha256":"f2e5286571dc45e78432bcb966ac1ab25b563e6d32946561df03d3fe9cb8c319"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J4k3kWksem5M9klX9cZpsO/jPbVA/S0UpXYyqOQJG2mno7PvrAU+dcit7EGgxP/3OElbcsW/lo1vI6gMucK2BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T02:42:21.501847Z","bundle_sha256":"52a7769c0df505a35fad05e07956308c663c36514d595aedbaf463fbe43a8e03"}}