{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:S7Q3UJ3KJLQ26JJVILSWVEWZWR","short_pith_number":"pith:S7Q3UJ3K","schema_version":"1.0","canonical_sha256":"97e1ba276a4ae1af253542e56a92d9b4425b62cb779509f462765b934f6ffc9f","source":{"kind":"arxiv","id":"1912.01530","version":2},"attestation_state":"computed","paper":{"title":"On the Validity of Bayesian Neural Networks for Uncertainty Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Brian Mac Namee, John Mitros","submitted_at":"2019-12-03T17:18:08Z","abstract_excerpt":"Deep neural networks (DNN) are versatile parametric models utilised successfully in a diverse number of tasks and domains. However, they have limitations---particularly from their lack of robustness and over-sensitivity to out of distribution samples. Bayesian Neural Networks, due to their formulation under the Bayesian framework, provide a principled approach to building neural networks that address these limitations. This paper describes a study that empirically evaluates and compares Bayesian Neural Networks to their equivalent point estimate Deep Neural Networks to quantify the predictive "},"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":"1912.01530","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-03T17:18:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8949235c0584be70976e31021a7aab961bf73727d1e072aeaf731803c97122c2","abstract_canon_sha256":"f9deb3bf2a413254158bf75ec17c3ffa813669899252bafc5aaf71d0d0f2c007"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:28:57.381331Z","signature_b64":"D3HOWIMpv73KRy0lwsfuSkE4mw54AK8Bj9NPar7AnoElScaMXY9Gnph7SXg3jT7WULPUB/eqWPz4rwOgAN8dAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97e1ba276a4ae1af253542e56a92d9b4425b62cb779509f462765b934f6ffc9f","last_reissued_at":"2026-07-05T00:28:57.380828Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:28:57.380828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Validity of Bayesian Neural Networks for Uncertainty Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Brian Mac Namee, John Mitros","submitted_at":"2019-12-03T17:18:08Z","abstract_excerpt":"Deep neural networks (DNN) are versatile parametric models utilised successfully in a diverse number of tasks and domains. However, they have limitations---particularly from their lack of robustness and over-sensitivity to out of distribution samples. Bayesian Neural Networks, due to their formulation under the Bayesian framework, provide a principled approach to building neural networks that address these limitations. This paper describes a study that empirically evaluates and compares Bayesian Neural Networks to their equivalent point estimate Deep Neural Networks to quantify the predictive "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.01530","kind":"arxiv","version":2},"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/1912.01530/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":"1912.01530","created_at":"2026-07-05T00:28:57.380887+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.01530v2","created_at":"2026-07-05T00:28:57.380887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.01530","created_at":"2026-07-05T00:28:57.380887+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7Q3UJ3KJLQ2","created_at":"2026-07-05T00:28:57.380887+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7Q3UJ3KJLQ26JJV","created_at":"2026-07-05T00:28:57.380887+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7Q3UJ3K","created_at":"2026-07-05T00:28:57.380887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21493","citing_title":"Don't Collapse Your Features: Why CenterLoss Hurts OOD Detection and Multi-Scale Mahalanobis Wins","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S7Q3UJ3KJLQ26JJVILSWVEWZWR","json":"https://pith.science/pith/S7Q3UJ3KJLQ26JJVILSWVEWZWR.json","graph_json":"https://pith.science/api/pith-number/S7Q3UJ3KJLQ26JJVILSWVEWZWR/graph.json","events_json":"https://pith.science/api/pith-number/S7Q3UJ3KJLQ26JJVILSWVEWZWR/events.json","paper":"https://pith.science/paper/S7Q3UJ3K"},"agent_actions":{"view_html":"https://pith.science/pith/S7Q3UJ3KJLQ26JJVILSWVEWZWR","download_json":"https://pith.science/pith/S7Q3UJ3KJLQ26JJVILSWVEWZWR.json","view_paper":"https://pith.science/paper/S7Q3UJ3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.01530&json=true","fetch_graph":"https://pith.science/api/pith-number/S7Q3UJ3KJLQ26JJVILSWVEWZWR/graph.json","fetch_events":"https://pith.science/api/pith-number/S7Q3UJ3KJLQ26JJVILSWVEWZWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7Q3UJ3KJLQ26JJVILSWVEWZWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7Q3UJ3KJLQ26JJVILSWVEWZWR/action/storage_attestation","attest_author":"https://pith.science/pith/S7Q3UJ3KJLQ26JJVILSWVEWZWR/action/author_attestation","sign_citation":"https://pith.science/pith/S7Q3UJ3KJLQ26JJVILSWVEWZWR/action/citation_signature","submit_replication":"https://pith.science/pith/S7Q3UJ3KJLQ26JJVILSWVEWZWR/action/replication_record"}},"created_at":"2026-07-05T00:28:57.380887+00:00","updated_at":"2026-07-05T00:28:57.380887+00:00"}