{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6NEP6GVKIZTQDTDS4U3XFNVY3O","short_pith_number":"pith:6NEP6GVK","schema_version":"1.0","canonical_sha256":"f348ff1aaa466701cc72e53772b6b8dba97543efdf1b533544ce66bdcabdc49c","source":{"kind":"arxiv","id":"2402.13410","version":1},"attestation_state":"computed","paper":{"title":"Bayesian Neural Networks with Domain Knowledge Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel P. Jeong, Dylan Sam, J. Zico Kolter, Rattana Pukdee, Yewon Byun","submitted_at":"2024-02-20T22:34:53Z","abstract_excerpt":"Bayesian neural networks (BNNs) have recently gained popularity due to their ability to quantify model uncertainty. However, specifying a prior for BNNs that captures relevant domain knowledge is often extremely challenging. In this work, we propose a framework for integrating general forms of domain knowledge (i.e., any knowledge that can be represented by a loss function) into a BNN prior through variational inference, while enabling computationally efficient posterior inference and sampling. Specifically, our approach results in a prior over neural network weights that assigns high probabil"},"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":"2402.13410","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T22:34:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4a65df6ef3ed701038b6b5427eb401fe33d4d6aa7ecadeb9c3d3c20dc52d9d1b","abstract_canon_sha256":"6d0a901e81b34f8a0da74cf07e4eb8615d3dad5b9dc1def1cd6d40d7310e90d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:31.687986Z","signature_b64":"bpXNdSbklPcUKHcoxnaTiq9gSUQteH//XgeTLWWU9mtN0PQPu1wL717T0GE+S+LTJezSvsJHPOK/ejpH4NpsBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f348ff1aaa466701cc72e53772b6b8dba97543efdf1b533544ce66bdcabdc49c","last_reissued_at":"2026-07-05T07:47:31.687495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:31.687495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Neural Networks with Domain Knowledge Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel P. Jeong, Dylan Sam, J. Zico Kolter, Rattana Pukdee, Yewon Byun","submitted_at":"2024-02-20T22:34:53Z","abstract_excerpt":"Bayesian neural networks (BNNs) have recently gained popularity due to their ability to quantify model uncertainty. However, specifying a prior for BNNs that captures relevant domain knowledge is often extremely challenging. In this work, we propose a framework for integrating general forms of domain knowledge (i.e., any knowledge that can be represented by a loss function) into a BNN prior through variational inference, while enabling computationally efficient posterior inference and sampling. Specifically, our approach results in a prior over neural network weights that assigns high probabil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13410","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/2402.13410/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":"2402.13410","created_at":"2026-07-05T07:47:31.687552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13410v1","created_at":"2026-07-05T07:47:31.687552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13410","created_at":"2026-07-05T07:47:31.687552+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NEP6GVKIZTQ","created_at":"2026-07-05T07:47:31.687552+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NEP6GVKIZTQDTDS","created_at":"2026-07-05T07:47:31.687552+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NEP6GVK","created_at":"2026-07-05T07:47:31.687552+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29448","citing_title":"Scalable Bayesian Spatial Mixture Modelling for Remote Sensing Image Segmentation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2412.12870","citing_title":"Physically Interpretable World Models via Weakly Supervised Representation Learning","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NEP6GVKIZTQDTDS4U3XFNVY3O","json":"https://pith.science/pith/6NEP6GVKIZTQDTDS4U3XFNVY3O.json","graph_json":"https://pith.science/api/pith-number/6NEP6GVKIZTQDTDS4U3XFNVY3O/graph.json","events_json":"https://pith.science/api/pith-number/6NEP6GVKIZTQDTDS4U3XFNVY3O/events.json","paper":"https://pith.science/paper/6NEP6GVK"},"agent_actions":{"view_html":"https://pith.science/pith/6NEP6GVKIZTQDTDS4U3XFNVY3O","download_json":"https://pith.science/pith/6NEP6GVKIZTQDTDS4U3XFNVY3O.json","view_paper":"https://pith.science/paper/6NEP6GVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13410&json=true","fetch_graph":"https://pith.science/api/pith-number/6NEP6GVKIZTQDTDS4U3XFNVY3O/graph.json","fetch_events":"https://pith.science/api/pith-number/6NEP6GVKIZTQDTDS4U3XFNVY3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NEP6GVKIZTQDTDS4U3XFNVY3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NEP6GVKIZTQDTDS4U3XFNVY3O/action/storage_attestation","attest_author":"https://pith.science/pith/6NEP6GVKIZTQDTDS4U3XFNVY3O/action/author_attestation","sign_citation":"https://pith.science/pith/6NEP6GVKIZTQDTDS4U3XFNVY3O/action/citation_signature","submit_replication":"https://pith.science/pith/6NEP6GVKIZTQDTDS4U3XFNVY3O/action/replication_record"}},"created_at":"2026-07-05T07:47:31.687552+00:00","updated_at":"2026-07-05T07:47:31.687552+00:00"}