{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:X3JYHZXBSG7CI7RFZJWZAL7KEI","short_pith_number":"pith:X3JYHZXB","schema_version":"1.0","canonical_sha256":"bed383e6e191be247e25ca6d902fea2204ad45ee7c09902f980bfa70863a3840","source":{"kind":"arxiv","id":"2001.10995","version":1},"attestation_state":"computed","paper":{"title":"The Case for Bayesian Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Gordon Wilson","submitted_at":"2020-01-29T18:08:52Z","abstract_excerpt":"The key distinguishing property of a Bayesian approach is marginalization instead of optimization, not the prior, or Bayes rule. Bayesian inference is especially compelling for deep neural networks. (1) Neural networks are typically underspecified by the data, and can represent many different but high performing models corresponding to different settings of parameters, which is exactly when marginalization will make the biggest difference for both calibration and accuracy. (2) Deep ensembles have been mistaken as competing approaches to Bayesian methods, but can be seen as approximate Bayesian"},"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":"2001.10995","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-29T18:08:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"db1586d614508c84a5a9f6e23717f54f9e5da3b052ac5bf6483eb18f8e576093","abstract_canon_sha256":"d1c32793325ca6fee103a544ec09dccdb62948779cbe8a3d436c77385d2c13d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:37:14.180670Z","signature_b64":"g1qd8d1fHNv4p2jePEpu5WSPACnzdN6+1w61OZ3xgW4+38qSkPCufk0UNapobml+V73/T+F8oeK5dlXbN8FfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bed383e6e191be247e25ca6d902fea2204ad45ee7c09902f980bfa70863a3840","last_reissued_at":"2026-07-05T00:37:14.180256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:37:14.180256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Case for Bayesian Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Gordon Wilson","submitted_at":"2020-01-29T18:08:52Z","abstract_excerpt":"The key distinguishing property of a Bayesian approach is marginalization instead of optimization, not the prior, or Bayes rule. Bayesian inference is especially compelling for deep neural networks. (1) Neural networks are typically underspecified by the data, and can represent many different but high performing models corresponding to different settings of parameters, which is exactly when marginalization will make the biggest difference for both calibration and accuracy. (2) Deep ensembles have been mistaken as competing approaches to Bayesian methods, but can be seen as approximate Bayesian"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.10995","kind":"arxiv","version":1},"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/2001.10995/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":"2001.10995","created_at":"2026-07-05T00:37:14.180306+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.10995v1","created_at":"2026-07-05T00:37:14.180306+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.10995","created_at":"2026-07-05T00:37:14.180306+00:00"},{"alias_kind":"pith_short_12","alias_value":"X3JYHZXBSG7C","created_at":"2026-07-05T00:37:14.180306+00:00"},{"alias_kind":"pith_short_16","alias_value":"X3JYHZXBSG7CI7RF","created_at":"2026-07-05T00:37:14.180306+00:00"},{"alias_kind":"pith_short_8","alias_value":"X3JYHZXB","created_at":"2026-07-05T00:37:14.180306+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20417","citing_title":"Neural network surrogates with uncertainty quantification for inverse problems in partial differential equations","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X3JYHZXBSG7CI7RFZJWZAL7KEI","json":"https://pith.science/pith/X3JYHZXBSG7CI7RFZJWZAL7KEI.json","graph_json":"https://pith.science/api/pith-number/X3JYHZXBSG7CI7RFZJWZAL7KEI/graph.json","events_json":"https://pith.science/api/pith-number/X3JYHZXBSG7CI7RFZJWZAL7KEI/events.json","paper":"https://pith.science/paper/X3JYHZXB"},"agent_actions":{"view_html":"https://pith.science/pith/X3JYHZXBSG7CI7RFZJWZAL7KEI","download_json":"https://pith.science/pith/X3JYHZXBSG7CI7RFZJWZAL7KEI.json","view_paper":"https://pith.science/paper/X3JYHZXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.10995&json=true","fetch_graph":"https://pith.science/api/pith-number/X3JYHZXBSG7CI7RFZJWZAL7KEI/graph.json","fetch_events":"https://pith.science/api/pith-number/X3JYHZXBSG7CI7RFZJWZAL7KEI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X3JYHZXBSG7CI7RFZJWZAL7KEI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X3JYHZXBSG7CI7RFZJWZAL7KEI/action/storage_attestation","attest_author":"https://pith.science/pith/X3JYHZXBSG7CI7RFZJWZAL7KEI/action/author_attestation","sign_citation":"https://pith.science/pith/X3JYHZXBSG7CI7RFZJWZAL7KEI/action/citation_signature","submit_replication":"https://pith.science/pith/X3JYHZXBSG7CI7RFZJWZAL7KEI/action/replication_record"}},"created_at":"2026-07-05T00:37:14.180306+00:00","updated_at":"2026-07-05T00:37:14.180306+00:00"}