{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MSKBRUNUDOXCT5CTHKY6O7T4VF","short_pith_number":"pith:MSKBRUNU","schema_version":"1.0","canonical_sha256":"649418d1b41bae29f4533ab1e77e7ca95ce26e8c510cfd22f830a6af5f433453","source":{"kind":"arxiv","id":"1904.02063","version":4},"attestation_state":"computed","paper":{"title":"Generalized Variational Inference: Three arguments for deriving new Posteriors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Jack Jewson, Jeremias Knoblauch, Theodoros Damoulas","submitted_at":"2019-04-03T15:31:46Z","abstract_excerpt":"We advocate an optimization-centric view on and introduce a novel generalization of Bayesian inference. Our inspiration is the representation of Bayes' rule as infinite-dimensional optimization problem (Csiszar, 1975; Donsker and Varadhan; 1975, Zellner; 1988). First, we use it to prove an optimality result of standard Variational Inference (VI): Under the proposed view, the standard Evidence Lower Bound (ELBO) maximizing VI posterior is preferable to alternative approximations of the Bayesian posterior. Next, we argue for generalizing standard Bayesian inference. The need for this arises in s"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1904.02063","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-04-03T15:31:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"50f922af5f8fb810ecb88efc3dd6f38195ec840025b52dc78a36c09cd35fedd3","abstract_canon_sha256":"54c64f839917fd2ba80f2f6816be29fe554764d2fb6f1f91556dd70bfbe74b22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:25:49.675380Z","signature_b64":"uumdg0W0jFSVaIg/Xj9txTkPccJ+HvO2jD40rAF2xwaLyIr/TXsreOwQK6c2GRPEnu/UQZ2EPmry5tYSIslwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"649418d1b41bae29f4533ab1e77e7ca95ce26e8c510cfd22f830a6af5f433453","last_reissued_at":"2026-07-05T00:25:49.674884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:25:49.674884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalized Variational Inference: Three arguments for deriving new Posteriors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Jack Jewson, Jeremias Knoblauch, Theodoros Damoulas","submitted_at":"2019-04-03T15:31:46Z","abstract_excerpt":"We advocate an optimization-centric view on and introduce a novel generalization of Bayesian inference. Our inspiration is the representation of Bayes' rule as infinite-dimensional optimization problem (Csiszar, 1975; Donsker and Varadhan; 1975, Zellner; 1988). First, we use it to prove an optimality result of standard Variational Inference (VI): Under the proposed view, the standard Evidence Lower Bound (ELBO) maximizing VI posterior is preferable to alternative approximations of the Bayesian posterior. Next, we argue for generalizing standard Bayesian inference. The need for this arises in s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02063","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/1904.02063/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1904.02063","created_at":"2026-07-05T00:25:49.674943+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.02063v4","created_at":"2026-07-05T00:25:49.674943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02063","created_at":"2026-07-05T00:25:49.674943+00:00"},{"alias_kind":"pith_short_12","alias_value":"MSKBRUNUDOXC","created_at":"2026-07-05T00:25:49.674943+00:00"},{"alias_kind":"pith_short_16","alias_value":"MSKBRUNUDOXCT5CT","created_at":"2026-07-05T00:25:49.674943+00:00"},{"alias_kind":"pith_short_8","alias_value":"MSKBRUNU","created_at":"2026-07-05T00:25:49.674943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21714","citing_title":"A Tutorial on Bregman Projection in Statistics","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26881","citing_title":"Robust ensemble Kalman filtering under observation noise misspecification via diffusion score matching","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10385","citing_title":"Regret Analysis of Guided Diffusion for Black-Box Optimization over Structured Inputs","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10378","citing_title":"Uncertainty in Physics and AI: Taxonomy, Quantification, and Validation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05513","citing_title":"From Unsupervised to Guided Clustering: A Variational Implementation","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MSKBRUNUDOXCT5CTHKY6O7T4VF","json":"https://pith.science/pith/MSKBRUNUDOXCT5CTHKY6O7T4VF.json","graph_json":"https://pith.science/api/pith-number/MSKBRUNUDOXCT5CTHKY6O7T4VF/graph.json","events_json":"https://pith.science/api/pith-number/MSKBRUNUDOXCT5CTHKY6O7T4VF/events.json","paper":"https://pith.science/paper/MSKBRUNU"},"agent_actions":{"view_html":"https://pith.science/pith/MSKBRUNUDOXCT5CTHKY6O7T4VF","download_json":"https://pith.science/pith/MSKBRUNUDOXCT5CTHKY6O7T4VF.json","view_paper":"https://pith.science/paper/MSKBRUNU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.02063&json=true","fetch_graph":"https://pith.science/api/pith-number/MSKBRUNUDOXCT5CTHKY6O7T4VF/graph.json","fetch_events":"https://pith.science/api/pith-number/MSKBRUNUDOXCT5CTHKY6O7T4VF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MSKBRUNUDOXCT5CTHKY6O7T4VF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MSKBRUNUDOXCT5CTHKY6O7T4VF/action/storage_attestation","attest_author":"https://pith.science/pith/MSKBRUNUDOXCT5CTHKY6O7T4VF/action/author_attestation","sign_citation":"https://pith.science/pith/MSKBRUNUDOXCT5CTHKY6O7T4VF/action/citation_signature","submit_replication":"https://pith.science/pith/MSKBRUNUDOXCT5CTHKY6O7T4VF/action/replication_record"}},"created_at":"2026-07-05T00:25:49.674943+00:00","updated_at":"2026-07-05T00:25:49.674943+00:00"}