{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4WDQR2BM5BJLJ3MEWL36HP2PDL","short_pith_number":"pith:4WDQR2BM","schema_version":"1.0","canonical_sha256":"e58708e82ce852b4ed84b2f7e3bf4f1aedf8e680e766752a4ca13202edd826ed","source":{"kind":"arxiv","id":"2306.12306","version":3},"attestation_state":"computed","paper":{"title":"Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Florian Seligmann, Gerhard Neumann, Michael Volpp, Philipp Becker","submitted_at":"2023-06-21T14:36:03Z","abstract_excerpt":"Bayesian deep learning (BDL) is a promising approach to achieve well-calibrated predictions on distribution-shifted data. Nevertheless, there exists no large-scale survey that evaluates recent SOTA methods on diverse, realistic, and challenging benchmark tasks in a systematic manner. To provide a clear picture of the current state of BDL research, we evaluate modern BDL algorithms on real-world datasets from the WILDS collection containing challenging classification and regression tasks, with a focus on generalization capability and calibration under distribution shift. We compare the algorith"},"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":"2306.12306","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-21T14:36:03Z","cross_cats_sorted":[],"title_canon_sha256":"8e53dae213a63d4494d123daf6dde0cc4a81ee184f592b1e992a21eaf4390f60","abstract_canon_sha256":"a53b389111f7cfc3bc3e5b830451bf6089294f832af0d6bf14b2630038a7687e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:48.460111Z","signature_b64":"mOOjCpSZNxkSy5vvAvRPDZp+v3clpfqEK6Wi87JD3zm+wRDn5XCO0OntyoRkpBQqMofJiyRZPD2tVJXgY6eZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e58708e82ce852b4ed84b2f7e3bf4f1aedf8e680e766752a4ca13202edd826ed","last_reissued_at":"2026-07-05T07:04:48.459713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:48.459713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Florian Seligmann, Gerhard Neumann, Michael Volpp, Philipp Becker","submitted_at":"2023-06-21T14:36:03Z","abstract_excerpt":"Bayesian deep learning (BDL) is a promising approach to achieve well-calibrated predictions on distribution-shifted data. Nevertheless, there exists no large-scale survey that evaluates recent SOTA methods on diverse, realistic, and challenging benchmark tasks in a systematic manner. To provide a clear picture of the current state of BDL research, we evaluate modern BDL algorithms on real-world datasets from the WILDS collection containing challenging classification and regression tasks, with a focus on generalization capability and calibration under distribution shift. We compare the algorith"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12306","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/2306.12306/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":"2306.12306","created_at":"2026-07-05T07:04:48.459770+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.12306v3","created_at":"2026-07-05T07:04:48.459770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12306","created_at":"2026-07-05T07:04:48.459770+00:00"},{"alias_kind":"pith_short_12","alias_value":"4WDQR2BM5BJL","created_at":"2026-07-05T07:04:48.459770+00:00"},{"alias_kind":"pith_short_16","alias_value":"4WDQR2BM5BJLJ3ME","created_at":"2026-07-05T07:04:48.459770+00:00"},{"alias_kind":"pith_short_8","alias_value":"4WDQR2BM","created_at":"2026-07-05T07:04:48.459770+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05982","citing_title":"THBKG: A Temporal Biomedical Knowledge Graph for Decision-Aligned Clinical Advancement Prediction","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4WDQR2BM5BJLJ3MEWL36HP2PDL","json":"https://pith.science/pith/4WDQR2BM5BJLJ3MEWL36HP2PDL.json","graph_json":"https://pith.science/api/pith-number/4WDQR2BM5BJLJ3MEWL36HP2PDL/graph.json","events_json":"https://pith.science/api/pith-number/4WDQR2BM5BJLJ3MEWL36HP2PDL/events.json","paper":"https://pith.science/paper/4WDQR2BM"},"agent_actions":{"view_html":"https://pith.science/pith/4WDQR2BM5BJLJ3MEWL36HP2PDL","download_json":"https://pith.science/pith/4WDQR2BM5BJLJ3MEWL36HP2PDL.json","view_paper":"https://pith.science/paper/4WDQR2BM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.12306&json=true","fetch_graph":"https://pith.science/api/pith-number/4WDQR2BM5BJLJ3MEWL36HP2PDL/graph.json","fetch_events":"https://pith.science/api/pith-number/4WDQR2BM5BJLJ3MEWL36HP2PDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4WDQR2BM5BJLJ3MEWL36HP2PDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4WDQR2BM5BJLJ3MEWL36HP2PDL/action/storage_attestation","attest_author":"https://pith.science/pith/4WDQR2BM5BJLJ3MEWL36HP2PDL/action/author_attestation","sign_citation":"https://pith.science/pith/4WDQR2BM5BJLJ3MEWL36HP2PDL/action/citation_signature","submit_replication":"https://pith.science/pith/4WDQR2BM5BJLJ3MEWL36HP2PDL/action/replication_record"}},"created_at":"2026-07-05T07:04:48.459770+00:00","updated_at":"2026-07-05T07:04:48.459770+00:00"}