{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GCV46TBVGCOAIBB5FS6QCWBBLZ","short_pith_number":"pith:GCV46TBV","schema_version":"1.0","canonical_sha256":"30abcf4c35309c04043d2cbd0158215e66ba83ba31eacdcdf9059c232e099559","source":{"kind":"arxiv","id":"2107.04562","version":4},"attestation_state":"computed","paper":{"title":"The Bayesian Learning Rule","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"H{\\aa}vard Rue, Mohammad Emtiyaz Khan","submitted_at":"2021-07-09T17:28:55Z","abstract_excerpt":"We show that many machine-learning algorithms are specific instances of a single algorithm called the \\emph{Bayesian learning rule}. The rule, derived from Bayesian principles, yields a wide-range of algorithms from fields such as optimization, deep learning, and graphical models. This includes classical algorithms such as ridge regression, Newton's method, and Kalman filter, as well as modern deep-learning algorithms such as stochastic-gradient descent, RMSprop, and Dropout. The key idea in deriving such algorithms is to approximate the posterior using candidate distributions estimated by usi"},"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":"2107.04562","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-07-09T17:28:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c9f52f32f5782da5f85b3f7d0c67b9f03ccb86f5a1e0dbb6ffde64b2824b45dd","abstract_canon_sha256":"78629bad055af5bde80e126811c0fbd43489b8a2cd560c2ec6d4ec5989088f36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:55.228300Z","signature_b64":"eeQrWCy2oc7f/r2OP9L4aFyz5yw1X7/SDioLDGZChNJeCmMFZjmzVVgoThRTwU+YkP/MzhIZ1w5AzT26SsSmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30abcf4c35309c04043d2cbd0158215e66ba83ba31eacdcdf9059c232e099559","last_reissued_at":"2026-07-05T08:28:55.227815Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:55.227815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Bayesian Learning Rule","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"H{\\aa}vard Rue, Mohammad Emtiyaz Khan","submitted_at":"2021-07-09T17:28:55Z","abstract_excerpt":"We show that many machine-learning algorithms are specific instances of a single algorithm called the \\emph{Bayesian learning rule}. The rule, derived from Bayesian principles, yields a wide-range of algorithms from fields such as optimization, deep learning, and graphical models. This includes classical algorithms such as ridge regression, Newton's method, and Kalman filter, as well as modern deep-learning algorithms such as stochastic-gradient descent, RMSprop, and Dropout. The key idea in deriving such algorithms is to approximate the posterior using candidate distributions estimated by usi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.04562","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/2107.04562/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":"2107.04562","created_at":"2026-07-05T08:28:55.227872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.04562v4","created_at":"2026-07-05T08:28:55.227872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.04562","created_at":"2026-07-05T08:28:55.227872+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCV46TBVGCOA","created_at":"2026-07-05T08:28:55.227872+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCV46TBVGCOAIBB5","created_at":"2026-07-05T08:28:55.227872+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCV46TBV","created_at":"2026-07-05T08:28:55.227872+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23591","citing_title":"Quantifying the Agreement Between Data-Influence and Data-Similarity to Understand LLM Behavior","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03134","citing_title":"Bayesian inference with sources of uncertainty: from confidence modelling to sparse estimation","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCV46TBVGCOAIBB5FS6QCWBBLZ","json":"https://pith.science/pith/GCV46TBVGCOAIBB5FS6QCWBBLZ.json","graph_json":"https://pith.science/api/pith-number/GCV46TBVGCOAIBB5FS6QCWBBLZ/graph.json","events_json":"https://pith.science/api/pith-number/GCV46TBVGCOAIBB5FS6QCWBBLZ/events.json","paper":"https://pith.science/paper/GCV46TBV"},"agent_actions":{"view_html":"https://pith.science/pith/GCV46TBVGCOAIBB5FS6QCWBBLZ","download_json":"https://pith.science/pith/GCV46TBVGCOAIBB5FS6QCWBBLZ.json","view_paper":"https://pith.science/paper/GCV46TBV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.04562&json=true","fetch_graph":"https://pith.science/api/pith-number/GCV46TBVGCOAIBB5FS6QCWBBLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/GCV46TBVGCOAIBB5FS6QCWBBLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCV46TBVGCOAIBB5FS6QCWBBLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCV46TBVGCOAIBB5FS6QCWBBLZ/action/storage_attestation","attest_author":"https://pith.science/pith/GCV46TBVGCOAIBB5FS6QCWBBLZ/action/author_attestation","sign_citation":"https://pith.science/pith/GCV46TBVGCOAIBB5FS6QCWBBLZ/action/citation_signature","submit_replication":"https://pith.science/pith/GCV46TBVGCOAIBB5FS6QCWBBLZ/action/replication_record"}},"created_at":"2026-07-05T08:28:55.227872+00:00","updated_at":"2026-07-05T08:28:55.227872+00:00"}