{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BS5GWIAQIIZBXMNAF5T42RHB4D","short_pith_number":"pith:BS5GWIAQ","schema_version":"1.0","canonical_sha256":"0cba6b201042321bb1a02f67cd44e1e0d4747710136ab8e8a064f0d501925b40","source":{"kind":"arxiv","id":"2501.11773","version":1},"attestation_state":"computed","paper":{"title":"Can Bayesian Neural Networks Make Confident Predictions?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Katharine Fisher, Youssef Marzouk","submitted_at":"2025-01-20T22:36:28Z","abstract_excerpt":"Bayesian inference promises a framework for principled uncertainty quantification of neural network predictions. Barriers to adoption include the difficulty of fully characterizing posterior distributions on network parameters and the interpretability of posterior predictive distributions. We demonstrate that under a discretized prior for the inner layer weights, we can exactly characterize the posterior predictive distribution as a Gaussian mixture. This setting allows us to define equivalence classes of network parameter values which produce the same likelihood (training error) and to relate"},"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":"2501.11773","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-20T22:36:28Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"c91308d43f3d8a81dec93942ec0c7e11fe2261339fa3b040b2beef03d5bf0f8d","abstract_canon_sha256":"132b6a7ae7f732ef9436e2d9cba0392519b5c019c494b869dde15173847ba70a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:13.572865Z","signature_b64":"AvaJYgIPd4RmjMpq1Lbs7eHxjwTwlC2cEyng3iGRXc0k2n5lPNX+bnBfq6izc5UXpsYNu3FyYFDOGNylRJNhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cba6b201042321bb1a02f67cd44e1e0d4747710136ab8e8a064f0d501925b40","last_reissued_at":"2026-07-05T10:03:13.572434Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:13.572434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Bayesian Neural Networks Make Confident Predictions?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Katharine Fisher, Youssef Marzouk","submitted_at":"2025-01-20T22:36:28Z","abstract_excerpt":"Bayesian inference promises a framework for principled uncertainty quantification of neural network predictions. Barriers to adoption include the difficulty of fully characterizing posterior distributions on network parameters and the interpretability of posterior predictive distributions. We demonstrate that under a discretized prior for the inner layer weights, we can exactly characterize the posterior predictive distribution as a Gaussian mixture. This setting allows us to define equivalence classes of network parameter values which produce the same likelihood (training error) and to relate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11773","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/2501.11773/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":"2501.11773","created_at":"2026-07-05T10:03:13.572500+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.11773v1","created_at":"2026-07-05T10:03:13.572500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11773","created_at":"2026-07-05T10:03:13.572500+00:00"},{"alias_kind":"pith_short_12","alias_value":"BS5GWIAQIIZB","created_at":"2026-07-05T10:03:13.572500+00:00"},{"alias_kind":"pith_short_16","alias_value":"BS5GWIAQIIZBXMNA","created_at":"2026-07-05T10:03:13.572500+00:00"},{"alias_kind":"pith_short_8","alias_value":"BS5GWIAQ","created_at":"2026-07-05T10:03:13.572500+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BS5GWIAQIIZBXMNAF5T42RHB4D","json":"https://pith.science/pith/BS5GWIAQIIZBXMNAF5T42RHB4D.json","graph_json":"https://pith.science/api/pith-number/BS5GWIAQIIZBXMNAF5T42RHB4D/graph.json","events_json":"https://pith.science/api/pith-number/BS5GWIAQIIZBXMNAF5T42RHB4D/events.json","paper":"https://pith.science/paper/BS5GWIAQ"},"agent_actions":{"view_html":"https://pith.science/pith/BS5GWIAQIIZBXMNAF5T42RHB4D","download_json":"https://pith.science/pith/BS5GWIAQIIZBXMNAF5T42RHB4D.json","view_paper":"https://pith.science/paper/BS5GWIAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.11773&json=true","fetch_graph":"https://pith.science/api/pith-number/BS5GWIAQIIZBXMNAF5T42RHB4D/graph.json","fetch_events":"https://pith.science/api/pith-number/BS5GWIAQIIZBXMNAF5T42RHB4D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BS5GWIAQIIZBXMNAF5T42RHB4D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BS5GWIAQIIZBXMNAF5T42RHB4D/action/storage_attestation","attest_author":"https://pith.science/pith/BS5GWIAQIIZBXMNAF5T42RHB4D/action/author_attestation","sign_citation":"https://pith.science/pith/BS5GWIAQIIZBXMNAF5T42RHB4D/action/citation_signature","submit_replication":"https://pith.science/pith/BS5GWIAQIIZBXMNAF5T42RHB4D/action/replication_record"}},"created_at":"2026-07-05T10:03:13.572500+00:00","updated_at":"2026-07-05T10:03:13.572500+00:00"}