{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4MZY2MXB6KUN26T33DVBOUETCT","short_pith_number":"pith:4MZY2MXB","schema_version":"1.0","canonical_sha256":"e3338d32e1f2a8dd7a7bd8ea17509314fcc622bf5937d495243998aa523a4025","source":{"kind":"arxiv","id":"2412.13286","version":2},"attestation_state":"computed","paper":{"title":"Posterior Mean Matching: Generative Modeling through Online Bayesian Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Blei, Emily Casleton, Michal Kucer, Sebastian Salazar, Yixin Wang","submitted_at":"2024-12-17T19:34:58Z","abstract_excerpt":"This paper introduces posterior mean matching (PMM), a new method for generative modeling that is grounded in Bayesian inference. PMM uses conjugate pairs of distributions to model complex data of various modalities like images and text, offering a flexible alternative to existing methods like diffusion models. PMM models iteratively refine noisy approximations of the target distribution using updates from online Bayesian inference. PMM is flexible because its mechanics are based on general Bayesian models. We demonstrate this flexibility by developing specialized examples: a generative PMM mo"},"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":"2412.13286","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T19:34:58Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b076e3b604b0c6b616fd231e9d85b8846e7e01e1c695716d3d372da373105900","abstract_canon_sha256":"8d66f25663bd93f99469b65ee126a5c1314157d856b3517f9c2845875cc4f6a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:19.855598Z","signature_b64":"Os9j/eu0rcEouogo7EbbYMOY/naBtNkI1x9GP5Df8n7ReoWl5cIhrL6yKz84d8+asQi4rW9MyDbxsJ8MzMybCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3338d32e1f2a8dd7a7bd8ea17509314fcc622bf5937d495243998aa523a4025","last_reissued_at":"2026-07-05T09:52:19.855148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:19.855148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Posterior Mean Matching: Generative Modeling through Online Bayesian Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Blei, Emily Casleton, Michal Kucer, Sebastian Salazar, Yixin Wang","submitted_at":"2024-12-17T19:34:58Z","abstract_excerpt":"This paper introduces posterior mean matching (PMM), a new method for generative modeling that is grounded in Bayesian inference. PMM uses conjugate pairs of distributions to model complex data of various modalities like images and text, offering a flexible alternative to existing methods like diffusion models. PMM models iteratively refine noisy approximations of the target distribution using updates from online Bayesian inference. PMM is flexible because its mechanics are based on general Bayesian models. We demonstrate this flexibility by developing specialized examples: a generative PMM mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13286","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.13286/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":"2412.13286","created_at":"2026-07-05T09:52:19.855211+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13286v2","created_at":"2026-07-05T09:52:19.855211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13286","created_at":"2026-07-05T09:52:19.855211+00:00"},{"alias_kind":"pith_short_12","alias_value":"4MZY2MXB6KUN","created_at":"2026-07-05T09:52:19.855211+00:00"},{"alias_kind":"pith_short_16","alias_value":"4MZY2MXB6KUN26T3","created_at":"2026-07-05T09:52:19.855211+00:00"},{"alias_kind":"pith_short_8","alias_value":"4MZY2MXB","created_at":"2026-07-05T09:52:19.855211+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4MZY2MXB6KUN26T33DVBOUETCT","json":"https://pith.science/pith/4MZY2MXB6KUN26T33DVBOUETCT.json","graph_json":"https://pith.science/api/pith-number/4MZY2MXB6KUN26T33DVBOUETCT/graph.json","events_json":"https://pith.science/api/pith-number/4MZY2MXB6KUN26T33DVBOUETCT/events.json","paper":"https://pith.science/paper/4MZY2MXB"},"agent_actions":{"view_html":"https://pith.science/pith/4MZY2MXB6KUN26T33DVBOUETCT","download_json":"https://pith.science/pith/4MZY2MXB6KUN26T33DVBOUETCT.json","view_paper":"https://pith.science/paper/4MZY2MXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13286&json=true","fetch_graph":"https://pith.science/api/pith-number/4MZY2MXB6KUN26T33DVBOUETCT/graph.json","fetch_events":"https://pith.science/api/pith-number/4MZY2MXB6KUN26T33DVBOUETCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4MZY2MXB6KUN26T33DVBOUETCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4MZY2MXB6KUN26T33DVBOUETCT/action/storage_attestation","attest_author":"https://pith.science/pith/4MZY2MXB6KUN26T33DVBOUETCT/action/author_attestation","sign_citation":"https://pith.science/pith/4MZY2MXB6KUN26T33DVBOUETCT/action/citation_signature","submit_replication":"https://pith.science/pith/4MZY2MXB6KUN26T33DVBOUETCT/action/replication_record"}},"created_at":"2026-07-05T09:52:19.855211+00:00","updated_at":"2026-07-05T09:52:19.855211+00:00"}