{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OQWZTE2LZ63ZJ2JULAPUSV6E7B","short_pith_number":"pith:OQWZTE2L","schema_version":"1.0","canonical_sha256":"742d99934bcfb794e934581f4957c4f849a96c235e65e2e2ec9d0f9e7c94fa4b","source":{"kind":"arxiv","id":"2401.12418","version":1},"attestation_state":"computed","paper":{"title":"Towards Improved Variational Inference for Deep Bayesian Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Sebastian W. Ober","submitted_at":"2024-01-23T00:40:20Z","abstract_excerpt":"Deep learning has revolutionized the last decade, being at the forefront of extraordinary advances in a wide range of tasks including computer vision, natural language processing, and reinforcement learning, to name but a few. However, it is well-known that deep models trained via maximum likelihood estimation tend to be overconfident and give poorly-calibrated predictions. Bayesian deep learning attempts to address this by placing priors on the model parameters, which are then combined with a likelihood to perform posterior inference. Unfortunately, for deep models, the true posterior is intr"},"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":"2401.12418","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-23T00:40:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"280bd93f9cbe71a4c5cbf06af774d8e08c14be6547fe6e2456247a08ba712ef4","abstract_canon_sha256":"43cd3c721a0385c9466d8e9cc92b109bd0c80691a2cd547267302ab038506ee2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:30.592990Z","signature_b64":"/gE91APXA6peSUU2DYaKqEAWQjL7nXbM32JdY/hdhZC7YYlbGvfQixzygZ+n7XsO7t0uJVy9CR6+LNfuuc6hCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"742d99934bcfb794e934581f4957c4f849a96c235e65e2e2ec9d0f9e7c94fa4b","last_reissued_at":"2026-07-05T07:36:30.592563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:30.592563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Improved Variational Inference for Deep Bayesian Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Sebastian W. Ober","submitted_at":"2024-01-23T00:40:20Z","abstract_excerpt":"Deep learning has revolutionized the last decade, being at the forefront of extraordinary advances in a wide range of tasks including computer vision, natural language processing, and reinforcement learning, to name but a few. However, it is well-known that deep models trained via maximum likelihood estimation tend to be overconfident and give poorly-calibrated predictions. Bayesian deep learning attempts to address this by placing priors on the model parameters, which are then combined with a likelihood to perform posterior inference. Unfortunately, for deep models, the true posterior is intr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12418","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/2401.12418/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":"2401.12418","created_at":"2026-07-05T07:36:30.592619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.12418v1","created_at":"2026-07-05T07:36:30.592619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12418","created_at":"2026-07-05T07:36:30.592619+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQWZTE2LZ63Z","created_at":"2026-07-05T07:36:30.592619+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQWZTE2LZ63ZJ2JU","created_at":"2026-07-05T07:36:30.592619+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQWZTE2L","created_at":"2026-07-05T07:36:30.592619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15987","citing_title":"Semantic-Aware Gaussian Process Calibration with Structured Layerwise Kernels for Deep Neural Networks","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQWZTE2LZ63ZJ2JULAPUSV6E7B","json":"https://pith.science/pith/OQWZTE2LZ63ZJ2JULAPUSV6E7B.json","graph_json":"https://pith.science/api/pith-number/OQWZTE2LZ63ZJ2JULAPUSV6E7B/graph.json","events_json":"https://pith.science/api/pith-number/OQWZTE2LZ63ZJ2JULAPUSV6E7B/events.json","paper":"https://pith.science/paper/OQWZTE2L"},"agent_actions":{"view_html":"https://pith.science/pith/OQWZTE2LZ63ZJ2JULAPUSV6E7B","download_json":"https://pith.science/pith/OQWZTE2LZ63ZJ2JULAPUSV6E7B.json","view_paper":"https://pith.science/paper/OQWZTE2L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.12418&json=true","fetch_graph":"https://pith.science/api/pith-number/OQWZTE2LZ63ZJ2JULAPUSV6E7B/graph.json","fetch_events":"https://pith.science/api/pith-number/OQWZTE2LZ63ZJ2JULAPUSV6E7B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQWZTE2LZ63ZJ2JULAPUSV6E7B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQWZTE2LZ63ZJ2JULAPUSV6E7B/action/storage_attestation","attest_author":"https://pith.science/pith/OQWZTE2LZ63ZJ2JULAPUSV6E7B/action/author_attestation","sign_citation":"https://pith.science/pith/OQWZTE2LZ63ZJ2JULAPUSV6E7B/action/citation_signature","submit_replication":"https://pith.science/pith/OQWZTE2LZ63ZJ2JULAPUSV6E7B/action/replication_record"}},"created_at":"2026-07-05T07:36:30.592619+00:00","updated_at":"2026-07-05T07:36:30.592619+00:00"}