{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YBJN77WGQMX5HBZ2IMAWSSSXIJ","short_pith_number":"pith:YBJN77WG","schema_version":"1.0","canonical_sha256":"c052dffec6832fd3873a4301694a5742696f7ab2c7114389b93bdd447e40bb0b","source":{"kind":"arxiv","id":"2106.14806","version":3},"attestation_state":"computed","paper":{"title":"Laplace Redux -- Effortless Bayesian Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Agustinus Kristiadi, Alexander Immer, Erik Daxberger, Matthias Bauer, Philipp Hennig, Runa Eschenhagen","submitted_at":"2021-06-28T15:30:40Z","abstract_excerpt":"Bayesian formulations of deep learning have been shown to have compelling theoretical properties and offer practical functional benefits, such as improved predictive uncertainty quantification and model selection. The Laplace approximation (LA) is a classic, and arguably the simplest family of approximations for the intractable posteriors of deep neural networks. Yet, despite its simplicity, the LA is not as popular as alternatives like variational Bayes or deep ensembles. This may be due to assumptions that the LA is expensive due to the involved Hessian computation, that it is difficult to i"},"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":"2106.14806","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-28T15:30:40Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"08e558bdf5264296f993d10f8a1c0763916691abb3c5b03c7eef5b8ba054a99f","abstract_canon_sha256":"5083c3e5515d82b2104d8633abeb38ca62213bfd5322ebfad34aaeeec5e0e24b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:39.943394Z","signature_b64":"tDXVSvzAkxLv84oCnSLF7MZ2PAsuwzIOevGuOltLTCyvvpLDnoXBrwmNcWfh5T0lHQHk/KVP3mp6eMLHPzw+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c052dffec6832fd3873a4301694a5742696f7ab2c7114389b93bdd447e40bb0b","last_reissued_at":"2026-07-05T04:04:39.942874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:39.942874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Laplace Redux -- Effortless Bayesian Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Agustinus Kristiadi, Alexander Immer, Erik Daxberger, Matthias Bauer, Philipp Hennig, Runa Eschenhagen","submitted_at":"2021-06-28T15:30:40Z","abstract_excerpt":"Bayesian formulations of deep learning have been shown to have compelling theoretical properties and offer practical functional benefits, such as improved predictive uncertainty quantification and model selection. The Laplace approximation (LA) is a classic, and arguably the simplest family of approximations for the intractable posteriors of deep neural networks. Yet, despite its simplicity, the LA is not as popular as alternatives like variational Bayes or deep ensembles. This may be due to assumptions that the LA is expensive due to the involved Hessian computation, that it is difficult to i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14806","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/2106.14806/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":"2106.14806","created_at":"2026-07-05T04:04:39.942950+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.14806v3","created_at":"2026-07-05T04:04:39.942950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14806","created_at":"2026-07-05T04:04:39.942950+00:00"},{"alias_kind":"pith_short_12","alias_value":"YBJN77WGQMX5","created_at":"2026-07-05T04:04:39.942950+00:00"},{"alias_kind":"pith_short_16","alias_value":"YBJN77WGQMX5HBZ2","created_at":"2026-07-05T04:04:39.942950+00:00"},{"alias_kind":"pith_short_8","alias_value":"YBJN77WG","created_at":"2026-07-05T04:04:39.942950+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08654","citing_title":"Operator learning for the 2D incompressible Navier-Stokes equations: a conformal prediction approach in the data-scarce regime","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23591","citing_title":"Quantifying the Agreement Between Data-Influence and Data-Similarity to Understand LLM Behavior","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26657","citing_title":"Target-Aware Bandit Allocation for Scalable Surrogate Optimization in Chemical Space","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2510.03046","citing_title":"Bayesian E(3)-Equivariant Interatomic Potential with Iterative Restratification of Many-body Message Passing","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YBJN77WGQMX5HBZ2IMAWSSSXIJ","json":"https://pith.science/pith/YBJN77WGQMX5HBZ2IMAWSSSXIJ.json","graph_json":"https://pith.science/api/pith-number/YBJN77WGQMX5HBZ2IMAWSSSXIJ/graph.json","events_json":"https://pith.science/api/pith-number/YBJN77WGQMX5HBZ2IMAWSSSXIJ/events.json","paper":"https://pith.science/paper/YBJN77WG"},"agent_actions":{"view_html":"https://pith.science/pith/YBJN77WGQMX5HBZ2IMAWSSSXIJ","download_json":"https://pith.science/pith/YBJN77WGQMX5HBZ2IMAWSSSXIJ.json","view_paper":"https://pith.science/paper/YBJN77WG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.14806&json=true","fetch_graph":"https://pith.science/api/pith-number/YBJN77WGQMX5HBZ2IMAWSSSXIJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YBJN77WGQMX5HBZ2IMAWSSSXIJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YBJN77WGQMX5HBZ2IMAWSSSXIJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YBJN77WGQMX5HBZ2IMAWSSSXIJ/action/storage_attestation","attest_author":"https://pith.science/pith/YBJN77WGQMX5HBZ2IMAWSSSXIJ/action/author_attestation","sign_citation":"https://pith.science/pith/YBJN77WGQMX5HBZ2IMAWSSSXIJ/action/citation_signature","submit_replication":"https://pith.science/pith/YBJN77WGQMX5HBZ2IMAWSSSXIJ/action/replication_record"}},"created_at":"2026-07-05T04:04:39.942950+00:00","updated_at":"2026-07-05T04:04:39.942950+00:00"}