{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:B7WWZXMYXOWVQ4V3JZVNIJANRF","short_pith_number":"pith:B7WWZXMY","schema_version":"1.0","canonical_sha256":"0fed6cdd98bbad5872bb4e6ad4240d8965de26ab1c0609eb2d311c84fa3834e3","source":{"kind":"arxiv","id":"1710.04759","version":2},"attestation_state":"computed","paper":{"title":"Bayesian Hypernetworks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Aaron Courville, Alexandre Lacoste, Chin-Wei Huang, David Krueger, Riashat Islam, Ryan Turner","submitted_at":"2017-10-13T00:27:57Z","abstract_excerpt":"We study Bayesian hypernetworks: a framework for approximate Bayesian inference in neural networks. A Bayesian hypernetwork $\\h$ is a neural network which learns to transform a simple noise distribution, $p(\\vec\\epsilon) = \\N(\\vec 0,\\mat I)$, to a distribution $q(\\pp) := q(h(\\vec\\epsilon))$ over the parameters $\\pp$ of another neural network (the \"primary network\")\\@. We train $q$ with variational inference, using an invertible $\\h$ to enable efficient estimation of the variational lower bound on the posterior $p(\\pp | \\D)$ via sampling. In contrast to most methods for Bayesian deep learning, "},"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":"1710.04759","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-13T00:27:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0247648136ff74523f4b473e1cc4c190e33c6096bfc9e62941d580f79d258087","abstract_canon_sha256":"baa15ccb30cacf81df338b9920c4ec2476bc9f197c43ab4bcc56d7e3f175ff2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:33.165444Z","signature_b64":"YkjhoY9NRrNksGY91BVtKL11iS81lCi0Es3qrr7K3CuGvDxO1MBkdEwPJBu+Q/L22O3DhVDZZaYIVZgGN8+nDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fed6cdd98bbad5872bb4e6ad4240d8965de26ab1c0609eb2d311c84fa3834e3","last_reissued_at":"2026-05-18T00:17:33.164665Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:33.164665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Hypernetworks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Aaron Courville, Alexandre Lacoste, Chin-Wei Huang, David Krueger, Riashat Islam, Ryan Turner","submitted_at":"2017-10-13T00:27:57Z","abstract_excerpt":"We study Bayesian hypernetworks: a framework for approximate Bayesian inference in neural networks. A Bayesian hypernetwork $\\h$ is a neural network which learns to transform a simple noise distribution, $p(\\vec\\epsilon) = \\N(\\vec 0,\\mat I)$, to a distribution $q(\\pp) := q(h(\\vec\\epsilon))$ over the parameters $\\pp$ of another neural network (the \"primary network\")\\@. We train $q$ with variational inference, using an invertible $\\h$ to enable efficient estimation of the variational lower bound on the posterior $p(\\pp | \\D)$ via sampling. In contrast to most methods for Bayesian deep learning, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.04759","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":""},"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":"1710.04759","created_at":"2026-05-18T00:17:33.164802+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.04759v2","created_at":"2026-05-18T00:17:33.164802+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.04759","created_at":"2026-05-18T00:17:33.164802+00:00"},{"alias_kind":"pith_short_12","alias_value":"B7WWZXMYXOWV","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"B7WWZXMYXOWVQ4V3","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"B7WWZXMY","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10679","citing_title":"U-FaceBP: Uncertainty-aware Bayesian Ensemble Deep Learning for Face Video-based Blood Pressure Estimation","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03150","citing_title":"HyperFitS -- Hypernetwork Fitting Spectra for metabolic quantification of ${}^1$H MR spectroscopic imaging","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01224","citing_title":"Lost in the Tower of Babel: The Adverse Effects of Incidental Multilingualism in LLMs","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00600","citing_title":"Possibilistic Predictive Uncertainty for Deep Learning","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06796","citing_title":"Instance-Adaptive Parametrization for Amortized Variational Inference","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B7WWZXMYXOWVQ4V3JZVNIJANRF","json":"https://pith.science/pith/B7WWZXMYXOWVQ4V3JZVNIJANRF.json","graph_json":"https://pith.science/api/pith-number/B7WWZXMYXOWVQ4V3JZVNIJANRF/graph.json","events_json":"https://pith.science/api/pith-number/B7WWZXMYXOWVQ4V3JZVNIJANRF/events.json","paper":"https://pith.science/paper/B7WWZXMY"},"agent_actions":{"view_html":"https://pith.science/pith/B7WWZXMYXOWVQ4V3JZVNIJANRF","download_json":"https://pith.science/pith/B7WWZXMYXOWVQ4V3JZVNIJANRF.json","view_paper":"https://pith.science/paper/B7WWZXMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.04759&json=true","fetch_graph":"https://pith.science/api/pith-number/B7WWZXMYXOWVQ4V3JZVNIJANRF/graph.json","fetch_events":"https://pith.science/api/pith-number/B7WWZXMYXOWVQ4V3JZVNIJANRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B7WWZXMYXOWVQ4V3JZVNIJANRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B7WWZXMYXOWVQ4V3JZVNIJANRF/action/storage_attestation","attest_author":"https://pith.science/pith/B7WWZXMYXOWVQ4V3JZVNIJANRF/action/author_attestation","sign_citation":"https://pith.science/pith/B7WWZXMYXOWVQ4V3JZVNIJANRF/action/citation_signature","submit_replication":"https://pith.science/pith/B7WWZXMYXOWVQ4V3JZVNIJANRF/action/replication_record"}},"created_at":"2026-05-18T00:17:33.164802+00:00","updated_at":"2026-05-18T00:17:33.164802+00:00"}